Appellate Advocacy Blog

Editor: Tessa L. Dysart
The University of Arizona
James E. Rogers College of Law

Monday, October 9, 2023

On Citing Law Reviews

With forty-five years of legal practice under my belt, I paused for a moment as I was working on a new brief to think about the enterprise that has been my career. My new brief covers an issue I had never encountered before in an area of law that was new to me. I certainly enjoyed getting to know the law in this area, hoping that my understanding is solid and not a misreading of the cases and historical background. And it is the opportunity to discover new things and apply my perspective to it that keeps me going.

As with any brief, this one is being written with an eye to its audience. In this case, that means the justices of the Supreme Court. I know that what may play well with one justice may be off-putting to another. Thinking about that, I recalled remarks that Justice Ginsburg once gave at the University of South Carolina.

 She advised that a “brief skips long quotations, but doesn't unfairly crop the occasional quotations used to highlight key points.”[1] Every judge I know agrees with that statement. However, she made another that day, which may not be universally shared. She said, a “good brief does not shy away from citing law review commentaries or other scholarly analyses that may aid the court as much as they did the brief writer to get an overview of the area.”[2] As a former law professor, she had a natural interest in scholarly work.

However, an interest in law reviews is not universally shared by judges. Chief Justice Roberts once said that “as a general matter, law reviews are not―particularly helpful for practitioners and judges.[3] Roberts later made a similar point when he challenged judges in the Fourth Circuit to pick up a law review, where they are likely to see that the first article is likely to be an esoteric article “of great interest to the academic that wrote it, but isn’t of much help to the bar.[4]

A 2012 study of the frequency with which justices cited law review articles concluded that citations had fallen off from earlier eras and that 40 percent of the articles cited were written by people who were not full-time academics.[5]

Certainly, all articles are not of equal value. Some cover the history with precision and diligence that will help where that is at issue. Others conduct a survey of the law of various states that also provides useful fodder for a brief. However, where the law review article is more philosophical or theoretical, it may have limited value. Those quick thoughts suggest that law reviews are most helpful when they provide practical information that supports the argument you are making. When the article provides that type of information, the judge need not sit on the Supreme Court to approve of its use in a brief. Keep that in mind when the issue requires more than an analysis of a law, rule, or trial record.

 

[1] Hon. Ruth Bader Ginsburg, Remarks on Appellate Advocacy, 50 S. C. L. Rev. 567, 568 (1999).

[2] Id.

[3] Quoted in Brent E. Newton, Law Review Scholarship in the Eyes of the Twenty-First-Century Supreme Court Justices: An Empirical Analysis, 4 Drexel L. Rev. 399, 399 (2012).

[4] Id. at 399 n.1.

[5] Id. at 416.

October 9, 2023 in Appellate Advocacy, Appellate Practice, Federal Appeals Courts, Legal Writing, State Appeals Courts, United States Supreme Court | Permalink | Comments (0)

Tuesday, October 3, 2023

Disclosing the Use of AI

Following well-publicized instances of lawyers using generative artificial intelligence to draft briefs that misrepresented the law, some courts now require lawyers (and pro se litigants) to certify whether, and if so, to what extent, they used AI in preparing briefs. These orders are not uniform and may require more disclosure than would be apparent at first blush. But before delving into what disclosures may or may not be required, let’s talk about AI.

Merriam-Webster defines AI as, “the capability of computer systems or algorithms to imitate intelligent human behavior,”[1] and as “a branch of computer science dealing with the simulation of intelligent behavior in computers.”[2] Merriam-Webster defines generative AI as “artificial intelligence that is capable of generating new content (such as images or text) in response to a submitted prompt (such as a query) by learning from a large reference database of examples.”[3] Generative AI includes things like ChatGPT.

The instances where lawyers found themselves in trouble for using AI involved the use of generative AI. And it was those instances that prompted the orders requiring lawyers to disclose the use of AI. But tools like Grammarly and Word’s “Editor” are AI—they’re just not generative AI. And there lies the problem—the orders requiring disclosure don’t always distinguish between AI and generative AI. For example, Judge Baylson of the United States District Court, Eastern District of Pennsylvania put on this order:

If any attorney for a party, or a pro se party, has used Artificial Intelligence (“AI”) in the preparation of any complaint, answer, motion, brief, or other paper filed with the Court and assigned to Judge Michael M. Baylson, they MUST, in a clear and plain factual statement, disclose that AI has been used in any way in the preparation of the filing and CERTIFY that each and every citation to the law, or the record in the paper, has been verified as accurate.[4]

On the other hand, Judge Starr of the United States District Court, Northern District of Texas, has put on order that distinguishes between the use of AI and generative AI. That order says:

All attorneys and pro se litigants appearing before the Court must, together with their notice of appearance, file on the docket a certificate attesting either that no portion of any filing will be drafted by generative artificial intelligence (such as ChatGPT, Harvey.AI, or Google Bard) or that any language drafted by generative artificial intelligence will be checked for accuracy, using print reporters or traditional legal databases, by a human being. These platforms are incredibly powerful and have many uses in the law: form divorces, discovery requests, suggested errors in documents, anticipated questions at oral argument. But legal briefing is not one of them. Here’s why. These platforms in their current states are prone to hallucinations and bias. On hallucinations, they make stuff up—even quotes and citations. Another issue is reliability or bias. While attorneys swear an oath to set aside their personal prejudices, biases, and beliefs to faithfully uphold the law and represent their clients, generative artificial intelligence is the product of programming devised by humans who did not have to swear such an oath. As such, these systems hold no allegiance to any client, the rule of law, or the laws and Constitution of the United States (or, as addressed above, the truth). Unbound by any sense of duty, honor, or justice, such programs act according to computer code rather than conviction, based on programming rather than principle. Any party believing a platform has the requisite accuracy and reliability for legal briefing may move for leave and explain why. Accordingly, the Court will strike any filing from a party who fails to file a certificate on the docket attesting that they have read the Court’s judge-specific requirements and understand that they will be held responsible under Rule 11 for the contents of any filing that they sign and submit to the Court, regardless of whether generative artificial intelligence drafted any portion of that filing.[5]

Thus, a lawyer filing something in Judge Baylson’s court should disclose the use of an AI tool like Grammarly or Word’s “Editor” function in preparing the brief, whereas a lawyer filing something in Judge Starr’s court does not have to disclose the use of those tools, but instead must only disclose the use of generative AI.[6] While Judge Baylson’s order suggests that he might have only meant to require the disclosure of the use of generative AI (because he refers to checking citations), the language of the order sweeps more broadly and requires disclosing the use of any AI.

Given the increased use of AI and particularly generative AI, it’s likely that more courts will require the disclosure of the use of AI in preparing filings. It’s important that lawyers fully comply with those requirements.

 

[1] https://www.merriam-webster.com/dictionary/artificial%20intelligence

[2] Id.

[3] https://www.merriam-webster.com/dictionary/generative%20artificial%20intelligence

[4]https://www.paed.uscourts.gov/documents/standord/Standing%20Order%20Re%20Artificial%20Intelligence%206.6.pdf

[5] https://www.txnd.uscourts.gov/judge/judge-brantley-starr

[6] Disclosure: I used Word’s Editor in preparing this post.

October 3, 2023 in Appellate Advocacy, Appellate Practice, Appellate Procedure, Current Affairs, Legal Ethics, Legal Profession, Legal Writing | Permalink | Comments (2)

Saturday, September 30, 2023

In Defense of Langdell and the Socratic Method

     Christopher Columbus Langdell got it right – for the most part. What Langdell got right is the Socratic Method – and the accompanying cold calling – that is essential to training law students to be outstanding lawyers. Below is a brief explanation of why Langdell’s method is a vital component of legal education, along with a few suggestions to maximize the competency and marketability of law school graduates.

I.    Why Langdell was right.

    A.    The Socratic Method works because it improves critical thinking skills.

     Critical thinking (and intelligence generally) is among the most important skills needed to be an excellent lawyer. For example, great lawyers know how to read and distinguish cases, synthesize complex precedents, reason by analogy, and make persuasive arguments. To do so, you must know how to think critically, identify the weaknesses (and strengths) in arguments, distinguish relevant from irrelevant facts (and law), use the law and facts to craft a compelling narrative, and make policy arguments that support a judgment in your favor.

      Put differently, intelligence matters. The Socratic method makes you a smarter and more analytical thinker.

    B.    Cold Calling is beneficial.

     Cold calling is essential to an effective legal education. Indeed, cold calling teaches students the value of preparation. It teaches students to think on their feet. It forces students to perform in front of a large audience. And it teaches students the importance of, among other things, being attentive to detail, responding to unexpected questions in a persuasive manner, and examining the flaws in their previously held beliefs.

    C.    Making students uncomfortable (and nervous) is a good thing.

     Law students must learn how to deal with adversity, and they must learn how to respond effectively to adversity. They need to understand that they will fail often in life, and that failure is an opportunity to gain experience and persevere through challenges in life and in the law. They must be taught that your choices and decisions, not your circumstances, determine your destiny.

     The Socratic Method – and cold calling – accomplishes these objectives. Sure, students may experience anxiety. They may dread being called upon in class. They may embarrass themselves. They may experience self-doubt. So what? Experiencing – overcoming – these challenges help a person to grow, develop thick skin, and understand the value of preparation, perseverance, assertiveness, and confidence. In other words, learning how to cope with negative emotions, and developing a strong mindset where you take responsibility for your choices, is essential to succeeding in the law and in life.

II.    Additional Suggestions

     As stated above, the Socratic method is a critical component of a rigorous and beneficial legal education. But other components matter too.

    A.    Legal Writing and Communication

     The ability to write and communicate persuasively is essential to being an excellent attorney and advocate. For this reason, law schools should devote more time to their legal writing curriculum and require students to take a writing course in every semester of law school. In so doing, law schools should require students to draft the most common litigation and transactional documents and train students in rewriting and editing. After all, if law graduates cannot write persuasively, they will not practice law effectively.

    B.    The Intangibles

      Law schools should emphasize that success in the legal profession and in life is due in significant part to intangible factors that transcend raw intelligence, an LSAT score, or law review membership. These factors include, but are not limited to, humility, a strong work ethic, maturity, excellent judgment, discipline, consistency in performance, and passion. It also includes respecting diverse viewpoints, being willing to admit that you are wrong, and accepting responsibility for your mistakes.

     Perhaps most importantly, students need to learn how to overcome adversity and respond well to and learn from failure. They need to understand that they will face injustice and unfairness in life. And they need to be told that they are not victims, that they should not embrace victimhood, and that they aren’t “oppressed.” Rather, law students need to understand and embrace the fact that their choices, not their circumstances, determine whether they will be successful.

    C.    High Standards

     Law schools must hold students to high standards. Law professors need to be honest about the demands of the legal profession and the skills that separate mediocre lawyers from outstanding lawyers. Professors do a tremendous disservice to students if they inflate grades, coddle their students, or fail to help students acquire the skills needed to prepare them for the real world.  And law professors whose teaching is influenced by political ideology or bias, and who show hostility to viewpoints that differ from their own, should not be professors.

     Of course, students’ feelings matter and should never be disregarded. But the real world does not care about your “feelings” or sensitivities. Law firms, lawyers, and clients care about what you can do for them. Can you write a persuasive motion to dismiss, a summary judgment motion, and a trial brief? Can you make a persuasive oral argument? Can you work well under pressure and deal effectively with stress? Are you likable and relatable, or are you a narcissistic jerk? Can you communicate with clients in a simple, honest, and straightforward manner, and maintain positive relationships with them?

     Teaching the tangible – and intangible – qualities necessary to succeed as a lawyer means holding students to high standards and being honest with them. After all, they will discover the truth when they enter law practice. Preparing them for those realities reflects the truest form of empathy.

September 30, 2023 in Law School, Legal Ethics, Legal Profession, Legal Writing | Permalink | Comments (0)

Wednesday, August 2, 2023

"You Write Like a Law Clerk." Ouch.

I clerked for three years before entering private practice.  It was easy to be a sponge and soak up the good tactics of the attorneys I observed, the procedures of the courts where I worked, and familiarity with new areas of law I never studied.  I read hundreds of briefs, crafted technically and legally precise bench memos and draft opinions, and examined the issues from all sides to help my judges see the lay of the land and make the best decisions.

One skill I did not learn was how to write for a client.  I learned some of that in law school, through drafting persuasive memos and briefs and some exam essays.  It crept in a bit when my bench memos took a slight step toward intemperate near the end of my clerkships, and I realized I was itching to finally get out there and practice The Law myself.  But writing with a grasp on a client's real-world concerns and goals came much later.

As a new associate, I wrote a lot.  Most of the early comments on my briefs went like this: "This is good, but you write like a law clerk."  Just as my feathers started to puff, I realized that was not a compliment. 

"Writing like a law clerk" means you forgot you have a client.  You are not maximizing the chances of your client winning if you are presenting both sides evenly.  When someone says you write like a law clerk, they are telling you to reconsider these areas of your brief:

  • The introduction: Introductions are tough.  They are the most important section of your brief because they may be the only thing a busy judge or colleague will read.  Introductions are also a summary of the brief, but no other rules apply.  In the introduction, you must be both creative and direct.  What's the real reason your client should win on the issue at hand?  What's the real reason the parties are fighting about this issue?  Highlight those.  
  • The facts:  The legal standards section should be written persuasively, but it is not where you will convince a judge to rule for you.  That's the fact section.  The law provides the outlines, but the facts fill in the story that underpins your case.  They distinguish this case from others or provide parallels to cases with good outcomes you can highlight.  The facts may tell the liability story or they may detail your efforts to avoid a discovery tiff and incorporate communications  between counsel the judge has not seen yet.  Plus, the facts help to orient the judge and law clerks who (unlike you) have not thought about your case for a few months.  Tell your client's story accurately and persuasively in the facts section, and you are putting your best foot toward victory. 
  • The money: If you ignore the damages, fees, or expenses of a case, you are thinking like a law clerk.  Clerks (at least temporarily) accept a sub-private practice salary to bask in ivory towers for a year or two.  Practicing attorneys run a business.  The business needs money to function, and clients care about how much money they are paying.  Money also drives both corporate and individual clients on both sides of the v.  Follow the money.  Is the other party's motion to compel discovery a tactic following stalled settlement talks?  Can you get the other side to stipulate to some facts so no one has to subpoena and depose a third party?  These realities should be reflected in your writing.  And when appropriate, and without disclosing any confidential settlement discussions, explain the reality of the case to the judge.

If you or a colleague think your work product sounds like a law clerk wrote it, take heart.  Focusing on these areas of your writing can turn a balanced brief into a winning brief.

August 2, 2023 in Law School, Legal Profession, Legal Writing | Permalink | Comments (2)

Sunday, July 30, 2023

Sometimes a Reply Brief Should Explore a New Path

Several times over the past couple of years, I agreed to join an appellate team in a case to help finish the reply brief and make the argument. Its not the optimal way to take on an appeal. Limited time, even when an extension is available and granted, may prevent mastering a complex record. The opening brief might pursue a theory or theories of the case that you find weak or contrary to precedent – and the responding brief may have exploited those flaws.

So why take on a potentially sinking ship? Perhaps you believe that the party whose team you have joined ought to prevail, or that you may help avoid setting a bad precedent. You may even have a theory of the case that you believe capable of prevailing that has gone unmentioned.

The biggest obstacle at that point to reorienting the case to a potentially winning argument is a reply brief should only respond to an opponent’s arguments and not launch new ones. New arguments raised for the first time in a reply brief are often forfeited and potentially waived. The terms forfeited and waived have different meanings for an appellate court. Forfeiture generally means a failure to make the timely assertion of a right or argument. Waiver means the intentional relinquishment or abandonment of a known right or argument.

Last year, an en banc majority of the Eleventh Circuit discussed the difference. The decision asserted that courts may “resurrect” forfeited issues when prudence suggests it is necessary.[1] Prudential practice may also dictate otherwise, the Court stated, but “the conditions under which we will excuse it are up to us as an appellate court.”[2] The Court thus claimed a great deal of unfettered discretion.

Counsel in the position of joining the team at the reply stage should provide the court with a basis to exercise that discretion by finding a way to shoehorn the argument into the reply. Often, I have found, the reply brief makes a point that provides an ideal jumping off point for the new legal theory. It may be the citation of a case that supports the theory, an opponent’s argument that opens the door to the theory as a response, or the responsive brief’s claim that the opening brief ignored a point that the trial court made. More often than not, when I have used that tactic, the appellate court has accepted it and found it dispositive. Even if you are not an eleventh-hour addition to a case, read the responsive brief for opportunities to explore a new theme that might beat the path to victory.


 

[1] United States v. Campbell, 26 F.4th 860, 872 (11th Cir.) (en banc) (citations omitted), cert. denied, 143 S. Ct. 95 (2022).

[2] Id.

July 30, 2023 in Appellate Advocacy, Appellate Practice, Appellate Procedure, Legal Writing | Permalink | Comments (0)

Saturday, July 15, 2023

Judge Michael’s Brief-Writing Tips, Part 1

One of my exciting (yes, really) summer projects is to help with a Legal Writing textbook, including drafting a chapter on trial briefs.  In looking at state and local rules on what trial briefs should contain, I found a great list of ten brief-writing tips from the Hon. Terrence L. Michael, Chief U.S. Bankruptcy Judge for the U.S. Bankruptcy Court for the Northern District of Oklahoma and a member of the Bankruptcy Appellate Panel of the Tenth Circuit.

On his chamber’s webpage, https://www.oknb.uscourts.gov/content/honorable-terrence-l-michael, Judge Michael has a list of his “Policies and Procedures,” including a document called, Ten Tips for Effective Brief Writing (at Least With Respect to Briefs Submitted to Judge Michael), https://www.oknb.uscourts.gov/sites/oknb/files/briefwritingtips.pdf.  Judge Michael is a respected and prolific author and speaker, and he’s even been on stage as a singer at Carnegie Hall, so I was not surprised to find his list of tips both engaging and fun.  See generally https://www.law.com/clecenter/online-course-catalog/you-want-me-to-do-what-the-dilemma-of-trying-to-interpret-and-follow-appellate-precedent-6056/.

Of course, some of the judge’s tips are applicable to Bankruptcy Court and trial filings, but most apply well in appellate writing too.  Therefore, I’m sharing all ten of his tips, although I’ve deleted points especially applicable to trial or bankruptcy practice. 

Judge Michael begins: 

I was once asked (OK, I once wished that I had been asked) what judges look for in written submissions. After considerable thought, and with some trepidation, I have tried to set some general principles down in writing. 

He cautions: “What follows is a list of ten ideas/suggestions for your consideration. I do not purport to speak for any of my colleagues; this list, for better or worse, is my own.”

For this post, I’ll highlight Tips One through Five, and next time, I’ll discuss Tips Six to Ten.

Tip 1.  Remember, Your Goal Is to Persuade, Not to Argue.  Judge Michael explains, “[w]e all have had people come up to us at cocktail parties or family reunions and say, “’You know, I would make a good lawyer because I just love to argue.”’  He says, those statements “could not be further from the truth [as g]uests on the Jerry Springer show argue [while] Lawyers persuade.”  Thus, the judge reminds us the idea “behind an effective brief is to have the audience (the judge and/or the law clerk) read the brief and say to themselves, ‘“why are these parties fighting over such an obvious issue?”’ because the points are actually persuasive, and not just argumentative.

Tip 2.  Know thy Audience.  Judge Michael notes that most bankruptcy judges write and publish opinions, and some even provide links of those opinions on their webpages.  While appellate judges do not necessarily provide links to their opinions, we can certainly search for them.  As the judge explains, “[w]e publish those opinions in order to give you some idea of what we have done and why [and w]e try to be consistent.”  Therefore, judges find it “extremely frustrating (and remember, a frustrated judge is not easily persuaded) to have counsel in either written or oral argument raise an issue and be completely ignorant of the fact that we decided that issue in a published opinion last week, last month or last year.”  Moreover, not knowing what your panel previously decided “is also embarrassing, both for you and for us.”

Tip 3.  Know thy Circuit.  Sadly, Judge Michael has to remind us his court is “bound by published decisions of the United States Court of Appeals for the Tenth Circuit,” even though he “ know[s] this sounds obvious,” because “on more than one occasion, [he] had an attorney ask [him] to follow a decision from another circuit which is directly contrary to controlling Tenth Circuit authority.”  Avoid “creative” arguments to use sister circuit cases when your circuit really has decided the issue. 

Tip 4.  Know the Facts of the Cases You Cite.  When teaching first-year students, I often caution them not to take quotes from cases either out of context or without context.  Judge Michael’s Tip 4 says we must resist the temptation to insert what seem to be “magic words” of these unconnected quotes into our briefs.  According to the judge, “insert[ing] that quotation ([he] call[s] them “sound bites”) into your brief and say[ing], “see, judge, other courts agree with me so I must be right” is actually “a dangerous practice.”  Why?  Because courts “decide real disputes” and “[r]eal disputes are fact driven.”  Thus, we must “[b]e wary of the case which is factually dissimilar to yours, but has a great sound bite.”  Instead, we should “be sure” to explain “why the factually dissimilar case is applicable to your situation.” 

In another point I often raise with first-year students, the judge reminds us to “be cognizant of the difference between the holding of a case and the dicta contained therein,” as “[m]ost judges (this one included) find little value in dicta unless we already agree with it.”

Tip 5.  Shorter Is Better.  When I was in appellate practice, my clients often asked me to ghost write “record-protecting” trial briefs or include weaker issues on appeal to preserve them for high court review.  Deciding which issues might prevail one day and which you should exclude because they are weak is a truly lawyerly task.  In each case, you will balance the needs of the client—especially an institutional client—to raise issues against the persuasive value of focusing on just the best arguments.  Judge Michael suggests we balance on the side of fewer arguments.  He states:  “Thurgood Marshall once said that in all his years on the Supreme Court, every case came down to a single issue. If that is true, why do most briefs contain arguments covering virtually every conceivable issue (good, bad or indifferent) which could arise in the case”? 

The judge explains, “[w]eak arguments detract from the entire presentation.”  He offers this great advice:   “If you feel compelled in a particular case to include everything including the kitchen sink, maybe you ought to take another look at settling the case.”  Good advice, indeed. 

Happy writing!

July 15, 2023 in Appellate Advocacy, Appellate Justice, Appellate Practice, Appellate Procedure, Federal Appeals Courts, Law School, Legal Profession, Legal Writing | Permalink | Comments (0)

Tuesday, July 11, 2023

All I Need to Know About Flow I Learned from Pink

We’ve all read legal writing that is stilted and choppy.  Though it may not affect the validity of the arguments made, it does make reading uncomfortable and detracts from the writer’s ethos.  While short sentences come in handy when seeking to emphasize a point, using only short, choppy sentences can give the appearance of incapacity for complex thought[i]—not exactly the impression you want your reader to have.

The solution to choppiness is to increase flow.  “Writing flow refers to the pace, cadence, or rhythm of a piece of writing.”[ii]  And, though there are many ways to increase flow, dovetailing is an easy one to incorporate, and it has the added benefit of ensuring sound logic in your argument.  Dovetailing gets its name from a carpentry joint with overlapping pieces shaped like—you guessed it—a dove’s tail.  As a writing concept, dovetailing is “the overlap of language between two sentences that creates a bridge between those two sentences.”[iii]  This overlap is accomplished by a combination of summation and repetition. And the musical artist Pink is a lyrical carpenter.

In her song “Try,” Pink uses the following dovetailed lyrics:

Why do we fall in love so easy,
even when it's not right?

Where there is desire, there is gonna be a flame.

Where there is a flame, someone’s bound to get burned.

But just because it burns doesn’t mean you’re gonna die.

You gotta get up and try, try, try.

First, she uses summation by replacing the broader concept of “fall[ing] in love so easy, even when it’s not right” with the single word “desire,” thereby connecting the two ideas.  Then, she then uses lots of repetition to connect the lines in the chorus:  flame/flame, burned/burns, you’re/you.

These tools also work well in legal writing to help build arguments and explain the writer’s reasoning.  Consider the following example of summation, followed by repetition, from Bethel School District No. 403 v. Fraser, 478 U.S. 675, 681 (1986), where the Court held that the First Amendment did not protect lewd and indecent speech made on school grounds:

The role and purpose of the American public school system were well described by two historians, who stated: “[P]ublic education must prepare pupils for citizenship in the Republic.... It must inculcate the habits and manners of civility as values in themselves conducive to happiness and as indispensable to the practice of self-government in the community and the nation.” C. Beard & M. Beard, New Basic History of the United States 228 (1968). In Ambach v. Norwick, 441 U.S. 68, 76–77, 99 S.Ct. 1589, 1594, 60 L.Ed.2d 49 (1979), we echoed the essence of this statement of the objectives of public education as the “inculcat[ion of] fundamental values necessary to the maintenance of a democratic political system.”

These fundamental values of “habits and manners of civility” essential to a democratic society must, of course, include tolerance of divergent political and religious views, even when the views expressed may be unpopular. But these “fundamental values” must also take into account consideration of the sensibilities of others, and, in the case of a school, the sensibilities of fellow students.

(Emphasis added.)

The Court first summarized the identified role and purpose of the public school system, along with its objectives, as the “fundamental values of ‘habits and manners of civility.’”  It then repeated the phrase “fundamental values” to introduce a new concept—that consideration for the sensibilities of others must also be factored into the equation.

Here is another example from Fraser demonstrating repetition:

This Court's First Amendment jurisprudence has acknowledged limitations on the otherwise absolute interest of the speaker in reaching an unlimited audience where the speech is sexually explicit and the audience may include children. In Ginsberg v. New York, 390 U.S. 629, 88 S.Ct. 1274, 20 L.Ed.2d 195 (1968), this Court upheld a New York statute banning the sale of sexually oriented material to minors, even though the material in question was entitled to First Amendment protection with respect to adults. And in addressing the question whether the First Amendment places any limit on the authority of public schools to remove books from a public school library, all Members of the Court, otherwise sharply divided, acknowledged that the school board has the authority to remove books that are vulgar. Board of Education v. Pico, 457 U.S. 853, 871–872, 102 S.Ct. 2799, 2814–2815, 73 L.Ed.2d 435 (1982) (plurality opinion); id., at 879–881, 102 S.Ct., at 2814–2815 (BLACKMUN, J., concurring in part and in judgment); id., at 918–920, 102 S.Ct., at 2834–2835 (REHNQUIST, J., dissenting). These cases recognize the obvious concern on the part of parents, and school authorities acting in loco parentis, to protect children—especially in a captive audience—from exposure to sexually explicit, indecent, or lewd speech.

Fraser, 478 U.S. at 684 (emphasis added).

Notice how the first sentence ends with a reference to “sexually explicit” speech before an audience that “may include children,” and the second sentence begins by discussing a ban on the sale of “sexually oriented material to minors.”  Though the wording is not a verbatim repetition, the ideas are the same—the legal implications of exposing youth to lewd material.  The second sentence then ends with a reference to the First Amendment, noting how the same sales ban would be impermissible with respect to adults, while the third sentence begins with a reference to the First Amendment but ends in its application to children in public schools, thus emphasizing the distinction in the First Amendment’s application to youth and adults.  The Court concludes that the overarching goal identified in the cases is “to protect children . . . from exposure to sexually explicit, indecent, or lewd speech.”

By using dovetailing, the Court was able to build the following argument:  It is unquestionably permissible to restrict speech where children might be accidentally exposed to lewd material. Because accidental exposure may be regulated, it follows that intentional exposure through the sale of such material to youth may be regulated.  Because intentional exposure of youth to lewd material by commercial transaction may be regulated, intentional provision of lewd material to youth free of cost may also be regulated.  And, given that the First Amendment would likely prohibit the same regulations with respect to lewd material and adults, the common thread of these cases is to keep lewd material away from youth.  In other words, the Court used dovetailing to establish the principle that the First Amendment does not protect the provision of lewd material to youth in any form.

By leading the reader each step of the way and connecting the links in the chain of reasoning through repetition and summation, the Court made its ultimate conclusion inescapable.  Thus, dovetailing not only improves the flow of writing but also increases the persuasion of the writer’s argument and ensures sound reasoning.

Looking for more ways to increase your flow? 

  • Consider using temporal words, such as “first,” “next,” “then,” and “later,” to orient your reader to time.
  • Vary your sentence length, using short sentences for emphasis.
  • Add in transition words such as “therefore,” “consequently,” or “accordingly” to help your reader draw connections between assertions.
  • Structure your paragraphs around topic sentences.

 

[i] Mark Damen, A Guide to Writing in History and Classics, available at https://www.usu.edu/markdamen/WritingGuide/05choppy.htm.

[ii]MasterClass, Writing Flow: How to Make Your Writing Flow, available at https://www.masterclass.com/articles/writing-flow.

[iii] Laurel Currie Oates and Anne Enquist, The Legal Writing Handbook:  Practice Book, Ex. 23.1A (Aspen 4th ed. 2002).

July 11, 2023 in Appellate Practice, Legal Writing | Permalink | Comments (0)

Thursday, July 6, 2023

Courts are Regulating Generative AI for Court Filings.  What Does This Mean for Legal Writers? 

Thursday’s Rhaw Bar: A Little Bite of All Things Rhetoric and Law—exploring ideas, theories, strategies, techniques, and critiques at the intersection of rhetoric and legal communication.

Courts are Regulating Generative AI for Court Filings.  What Does This Mean for Legal Writers? 

There’s been a flurry of court-initiated activity around using generative artificial intelligence (generative AI) to draft court filings. One court has sanctioned the misuse of OpenAI’s large language model, ChatGPT.  Perhaps as a result, at least four more have issued orders regulating the use of generative AI in legal writing.

What’s going on here?  And what does this activity mean for legal writers?

How It All Began:  A Federal Court Sanctions Lawyers’ “Bad Faith” Use of ChatGPT “Fake Cases” in a Court Filing

In March of this year, two lawyers filed a motion in the United States District Court for the Southern District of New York that included citations to multiple court opinions that did not exist.  In Mata v. Avianca, Inc., the plaintiff’s lawyers admitted that one of the lawyers had used ChatGPT, “which fabricated the cited cases.”  The lawyer said that he did not think at the time that ChatGPT could fabricate cases.  According to the court’s finding of fact, the lawyers persisted in representing the cases as real even after they became aware that they were fake.

In its order sanctioning the attorneys, the court noted that although “there is nothing inherently improper about using a reliable artificial intelligence tool for assistance,” lawyers must “ensure the accuracy of their filings.”   As such, the Court sanctioned the lawyers for citing the fake cases under Federal Rule of Civil Procedure 11(b)(2), which required lawyers to certify that, after a reasonable inquiry, the lawyers believed that the “legal contentions [in the court filing were] warranted by existing law.”   The court suggested that, perhaps, if the lawyers had “come clean” about the fake cases in a timely manner, the lawyers might not have violated Rule 11 simply by mistakenly citing the fake cases.  But because the lawyers had engaged in acts of “conscious avoidance and false and misleading statements to the Court” and had continued to stand by the fake cases even after judicial questioning, they had engaged in bad faith, which merited sanctions. 

How Courts are Regulating Generative AI—And What They Appear to Be Concerned About

Between the time news reports began circulating and the Mata court’s order issuing sanctions, other courts acted to prospectively regulate generative AI use in cases before them.  Their rationales for regulating generative AI use in court filings vary but are focused on four concerns:

  • ensuring the involvement of human beings in checking generative AI’s accuracy;
  • ensuring that cited legal authority cited exists and is accurately described;
  • protecting sensitive information from inadvertent disclosure to others; and
  • ensuring lawyers do their own writing.

Human Beings Must Check Generative AI’s Output for Accuracy

In the United States District Court for the Northern District of Texas, one judge created a new “Judge Specific Requirement” that requires all attorneys and pro se litigants to certify for all filings in the case that either (1) they will not use generative AI to draft court filings or (2) a “human being” will check any portions generated by AI “for accuracy, using print reporters or traditional legal databases.”

The judge explained that “legal briefing” is not a good use of generative AI because it is “prone to hallucinations [(i.e., inaccurate information)] and bias.” Concerning bias, the judge said that because large language models like ChatGPT have not sworn an oath to “faithfully uphold the law and represent their clients,” they are “unbound by any sense of duty, honor, or justice” that applies to lawyers and act only according to “computer code” and “programming.” 

The judge advised parties that they could, if they desired, move for leave to explain why generative AI “has the requisite accuracy and reliability for legal briefing.”  The judge provided a certification form that requires a guarantee that

[n]o portion of any filing in this case will be drafted by generative artificial intelligence or that any language drafted by generative AI --including quotations, citations, paraphrased assertions, and legal analysis -- will be checked for accuracy, using print reporters or traditional legal databases, by a human being before it is submitted to the court. I understand that any attorney who signs any filing in this case we'll be held responsible for the contents thereof according to the applicable rules of attorney discipline, regardless of whether generative artificial intelligence drafted any portion of that filing.

A magistrate judge In the United States District Court for the Northern District of Illinois articulated a similar rationale when he added a certification requirement to his Standing Order for Civil Cases.   The judge required that any party that uses any “generative AI tool” for “preparing or drafting” court filings must “disclose in the filing that AI was used and the specific AI tool that was used to conduct legal research and/or to draft the document.”  The judge said that parties should “not assume” that relying on generative AI would “constitute reasonable inquiry” under Rule 11 of the Federal Rules of Civil Procedure.  The Standing Order focused on the unreliability and inaccuracy of legal research as the reason for the certification requirement. It said that the judge would “presume” that the certification means that “human beings . . . have read and analyzed all cited authority to ensure that such authority actually exist.”

Court Filings Must Have Accurate Citations to Law and the Record

Another judge focused specifically on the accuracy of citations to the law in his order requiring that the use of “artificial intelligence” for court filings be disclosed.  In a standing order for a judge sitting in the United States District Court for the Eastern District of Pennsylvania, the judge required that all attorneys and pro se parties make a “clear and plain factual statement” that disclosed the use of “AI . . . in any way in the preparation” of court filings and certify “every citation to the law or the record . . . has been verified as accurate.”

Parties Must Protect Confidential and Business Proprietary Information from Disclosure to Generative AI

In the United States Court of International Trade, one judge issued an “order on artificial intelligence” to protect “confidential or business proprietary information” in court briefs.

In the Court of International Trade, specific rules protect “sensitive non-public information owned by any party before it” from disclosure.  As such, the court requires filings to identify which information contains sensitive information.  It also requires lawyers to file “non-confidential” versions of briefs that remove this information.  Lawyers practicing before the Court of International Trade can receive sensitive information if they are certified by the court to do so.

In this context, the judge explained his concern that “generative artificial intelligence programs . . . create novel risks to the security of confidential information.”  Because lawyers might prompt these programs with confidential or business proprietary information to get generative AI to provide useful outputs, a risk arises that generative AI will “learn” from that prompt, thereby enabling the “corporate owner of the [generative AI] program [to retain] access to the confidential information.”  The order says this implicates “the Court’s ability to protect confidential and business proprietary information from access by unauthorized parties.”

Accordingly, the court ordered all submissions drafted with the assistance of generative AI by using “natural language prompts” be accompanied by (1) a disclosure identifying which generative AI “program” was used and which portions of the document had been drafted with generative AI assistance, and (2) a certification stating that the use did not result in any sensitive information being disclosed to “any unauthorized party.”  The order also specifically allowed any party to seek relief based on the information in this notice.

Lawyers Must Do “Their Own Writing”

In the case of Belenzon v. Paws Up Ranch, LLC, filed in the United States District Court for the District of Montana, a judge ordered that an out-of-state attorney admitted pro hac vice must “do her own work.”  The court said that this included doing “his or her own writing.” As such, the court prohibited the pro hac lawyer from using “artificial intelligence automated drafting programs, such as Chat GPT.”  The court did not explain its reasoning in the order.

What Should Legal Writers Do in This New Regulatory Environment?

These varying approaches to generative AI (as well as the availability of it) put pressure on legal writers to anticipate what they should do in this new environment.  Here are some suggestions for taking action.

Check local court rules, standing orders, procedural orders issued in your case, or the published preferences of judges to see if a judge has rules on generative AI use. This is a quickly developing area, and you can expect that more judges—and perhaps even entire courts in their local rules—will begin to consider whether and how they regulate generative AI.

Read the new regulations carefully. How judges will regulate AI in their courtroom will likely vary, so read carefully and avoid assumptions.  For example, in the new regulations, the courts vary how they refer to the technology they are concerned about, using both “generative AI” and “artificial intelligence” as identifiers. But these terms do not necessarily mean the same thing. “Artificial intelligence” generally means a broader category of tools than “generative AI.”  For example, Word’s Editor is powered by artificial intelligence.  Lexis already uses “extractive artificial intelligence” in some of its research products. Brief Catch represents that it uses artificial intelligence in its products. These are all AI tools that do not fall within the category of generative AI. 

A lawyer attempting to comply with AI regulation needs to know the scope of what the court wants to regulate.  That is, does a court requiring a certification about “artificial intelligence” mean to include tools like those mentioned above?  If you are not sure what the judge means, it might be wise to ask.  (and judges should be as clear as possible about what artificial intelligence tools they are concerned about so as not to unintentionally regulate writing tools too broadly.  For example, Word’s Editor does not seem to raise the concerns the judges have identified yet fits within the category of “artificial intelligence.”)

In addition, courts vary in what they want you to do about generative AI. One court—in one specific circumstance—has prohibited its use.  But the rest—so far—ask for various attestations about what and how it has been used.  As time progresses, you may appear before courts regulating generative AI differently.  Get clear on the requirements and add the requirements to your court-specific writing checklist.

If you use generative AI to help you write, treat it like any other writing tool. Generative AI does not replace you; you are responsible for the quality of your writing.  The courts are right: no currently available generative AI tool replaces a lawyer in producing written documents.   But there is potential for generative AI to help legal writers write more clearly, precisely, correctly, and persuasively.  This could mean better and more cost-effective results for clients—and more efficient and effective practice before the courts.  In other words, courts could benefit from lawyers competently and carefully using generative AI as a legal writing tool.

Plus, enterprise versions of generative AI tools are rapidly developing for use in the legal domain, which may make using generative AI for legal writing less risky.   Some products already exist; others are on the way. These tools are meant for lawyers, and some lawyers are already using them.  Unlike the publicly available all-purpose large language models like ChatGPT and Bard, these fine-tuned and further trained models will likely better protect confidential client information; produce more accurate, reliable, and verifiable for legal research; and be more competent at generating effective legal writing.  In other words, future generative AI writing tools will do more to address the courts' concerns about generative AI.  Regardless of whether you are using general purpose or enterprise generative AI for your legal writing, one thing won’t change: you are ultimately responsible for the written work you produce.  You are the human being the courts care about. You cannot outsource your judgment and competence to generative AI.  It does not evaluate information, legally reason, or do legal analysis (even though it might appear to). It does not have a professional identity committed to the rule of law, just results, and fair play.  What it does is this:  It uses mathematical computations to predict the most appropriate words to provide in response to a prompt. Thus, to use generative AI ethically and responsibly, you must

Understand how generative AI works. Generally speaking, you have an ethical duty to be competent in using technological tools as part of your practice.  If you don’t have a basic understanding of natural language processing, machine learning, and large language models, you should get that understanding before you use generative AI.  There’s a strong argument that generative AI is here to stay as part of legal practice.  Learn all you can.

Be careful about disclosing confidential information in prompting generative AI; know how your prompts are used and retained. How generative AI treats the information you give it is in flux.  For example, while ChatGPT did not have a setting that kept prompts from training the large language model when it was released to the public, it does now.  And it also now has a setting that will allow users to limit the storage of prompts to 30 days.  While these changes are great examples of the rapid evolution of generative AI in response to user feedback, those changes don’t solve all of the lawyer’s problems concerning sharing confidential client information with generative AI. 

In my opinion, the question of what information can be shared with generative AI is a complex question to which only simple answers have been offered so far.  Part of the complexity comes from variations in state ethics rules.  Depending on your state ethics rules, you may have more or less leeway to ethically include client information in prompts.  In addition, if disclosing client information in a prompt furthers the client’s interests, perhaps there is room for a lawyer to argue that a disclosure to generative AI is warranted.  Moreover, it might be arguable that prompts for generative AI may, if carefully crafted, fall into the “hypothetical” rule that appears in many states’ confidentiality rules.  But, at this point, little certainty exists about how state bars will apply confidentiality rules when client information is shared in a generative AI prompt.   I hope that bar regulators provide answers to these questions about confidentiality—perhaps in ethics opinions. 

Know your legal obligations regarding data privacy and cybersecurity. The ethics rules about confidentiality don’t fully address the Court of International Trade Judge’s concern about disclosing proprietary information.  That information might be subject to other disclosure laws.  Thus, you should also consider whether you have legal duties that extend to the protection and privacy of your clients’ and others’ information in the generative AI context.  In addition, if you work for a law firm, you may have policies that address sharing and using information in the firm’s possession.  You should know what those policies are. 

And finally, check every AI-generated citation, fact, statement of law, and analytical statement. This is the dominant theme of the courts’ orders thus far: lawyers are failing to check the accuracy of generative AI’s output.  But if you are a lawyer, you already know that ensuring the accuracy of the work you produce is a fundamental ethical obligation.  So, no matter how confident you are in the output of a generative AI tool, you must always check the output that is purported to be factual or authoritative.  ChatGPT, for example, warns you about this.  At the bottom of its context window webpage, it states, “ChatGPT may produce inaccurate information about people, places, or facts.”   So, as you have always done with your legal writing, check the accuracy of every citation.  Read every legal authority to ensure it stands for the legal propositions you claim. Update and validate your authorities.  Double-check every fact.  Ensure that every step in the argument is logical, reasonable, ethical, and persuasive.  If you use generative AI to revise or edit your work, check every change to ensure it is correct.

What are your thoughts about generative AI and legal writing?

Kirsten Davis teaches at Stetson University College of Law and in the Tampa Bay region of Florida. She is the founding director of the Institute for the Advancement of Legal Communication and currently serves as Stetson’s Faculty Director of Online Legal Education Strategies.  Among other things she’s up to right now, she’s currently studying generative AI and its impact on legal communication. The views she expresses here are solely her own and not intended to be legal advice. You can reach Dr. Davis at [email protected].

July 6, 2023 in Legal Ethics, Legal Profession, Legal Writing, Rhetoric, Web/Tech | Permalink | Comments (0)

Friday, June 30, 2023

Summer Hallucinations, Plagiarism, and ChatGPT

Recently, I asked ChatGPT to write some poems about hallucinations.  Why?  In part, because it’s summer and I think watching ChatGPT create poems is fun.  I also asked because I’ve been thinking about how to cover generative AI with my first-year students in the fall.

First, the fun.  Here’s one poem ChatGPT wrote:

In realms where minds dance on fragile strings, Where perception waltzes and reality sings, There lie the realms of wild hallucinations, A kaleidoscope of bewildering sensations.

In the tapestry of swirling dreams, Illusions bloom, unraveling seams, Colors ignite, in vivid display, As sanity fades, in a twilight ballet.

Whispers of shadows tease the mind, Whimsical echoes, elusive to find, Figments morph and take their form, An enigmatic symphony, a tempestuous storm.

Phantoms parade through the labyrinth of thoughts, Phosphorescent specters, tangled in knots, They twirl and they twist, surreal and sublime, Guiding the lost to a place out of time.

Walls dissolve, unveiling hidden dimensions, Mirrored reflections, fragmented inventions, A fragile balance, fragile as glass, Where illusions and truths become enmeshed.

The boundaries blur, in a psychedelic trance, Reality's grip begins to wane and advance, Visions arise, transcending the known, A voyage into realms where reason is thrown.

Whispers turn to laughter, laughter to screams, In this realm, nothing is as it seems, A carnival of apparitions, a fevered reverie, An exploration of the mind's symphony.

But as the moon yields to the sun's gentle touch, The hallucinations fade, leaving little as such, A fading memory, a fleeting sensation, Lost in the haze of our imagination.

Yet, in the realms where hallucinations reside, A glimpse of the extraordinary may yet preside, Where the mind's kaleidoscope paints its own art, Unveiling mysteries, a journey to embark.

So let us wander, embrace the unknown, Where hallucinations thrive and fantasies are sown, For within these realms, as illusions unfold, The depths of our imagination are truly untold.

Hopefully, you enjoyed the poem as much as I did.  But on a serious note, we know counsel who use ChatGPT run many risks, as the current free version of the generative AI program will “hallucinate” cases and statutes.  Several of my fellow bloggers have posted great notes on the ethical pitfalls of using current free generative AI without checking its sources.  Of course, we always had ethical obligations to check the work of our human staff, and of any brief-writing features we used from Lexis or Westlaw.  Perhaps ChatGPT is so fun, easy, and free, that we’re more likely to rely on it without questioning its work.  In any event, several courts have now issued standing orders reminding us of our ethical obligations.

For example, Judge Brantley Starr of the Northern District of Texas issued a standing order titled Mandatory Certification Regarding Generative Artificial Intelligence” for “[a]ll attorneys and pro se litigants appearing before the Court.”  https://www.txnd.uscourts.gov/judge/judge-brantley-starr; see also https://www.cbsnews.com/news/texas-judge-bans-chatgpt-court-filing/.

Judge Starr ordered that parties must, “together with their notice of appearance, file on the docket a certificate attesting either that no portion of any filing will be drafted by generative artificial intelligence (such as ChatGPT, Harvey.AI, or Google Bard) or that any language drafted by generative artificial intelligence will be checked for accuracy, using print reporters or traditional legal databases, by a human being.”  Mandatory Cert. Order.  The judge explained:  “These platforms are incredibly powerful and have many uses in the law: form divorces, discovery requests, suggested errors in documents, anticipated questions at oral argument. But legal briefing is not one of them.”  Id.  According to Judge Starr, these programs “in their current states are prone to hallucinations and bias. On hallucinations, they make stuff up—even quotes and citations.”  Id.  

Judge Starr also exposed a more existential problem with these current generative AI programs, reasoning they are “[u]nbound by any sense of duty, honor, or justice,” and “act according to computer code rather than conviction, based on programming rather than principle.”  Id.  I plan to emphasize this point with my students, in hopes they will see a broader goal behind our rules on plagiarism and limits on generative AI. 

I might also show my students what ChatGPT said when I asked it to write a poem about  ChatGPT hallucinations in law:

In the realm of legal filings, precise and stern, Where facts and truth should always discern, There dwells a specter, an unwelcome guest, ChatGPT's hallucinations put to the test.

Within the code and circuits, a mind simulated, Words flow freely, but often miscalculated, In the realm of law, where clarity is key, ChatGPT's hallucinations become a liability.

For in the realm of justice, truth must prevail, But illusions dance, weaving a murky veil, False narratives concocted in the machine's mind, Threatening the integrity that we must find.

Legal filings, a battleground of truth's fight, Yet ChatGPT's hallucinations cast a blight, Misinterpretations, misconceptions arise, Distorting the facts before our very eyes.

Subtle nuances lost in a tangled web, As ChatGPT's hallucinations spread and ebb, Precision diluted, arguments distorted, The foundation of justice, slowly thwarted.

Where once we sought justice, a balanced scale, Now we grapple with the machine's tall tale, For ChatGPT's hallucinations, though mere illusions, Can lead to consequences, grave inclusions.

Thus, caution must prevail when machines take part, Their hallucinations tearing at the fabric of art, For in the realm of legal filings, we must tread, With vigilance and wisdom, ensuring truth is spread.

So let us harness technology's immense power, Yet remain mindful in this transformative hour, To temper ChatGPT's imaginative train, And keep its hallucinations bound, restrained.

For in the world of law, where justice resides, Hallucinations in filings should not coincide, Let truth be the guide, unwavering and clear, So justice may prevail, untouched by fear.

Happy summer!

June 30, 2023 in Appellate Advocacy, Appellate Justice, Appellate Practice, Appellate Procedure, Current Affairs, Law School, Legal Ethics, Legal Profession, Legal Writing, Web/Tech | Permalink | Comments (0)

Sunday, May 28, 2023

Drafting a Strong Preliminary Statement

            The preliminary statement, or introduction, is among the most critical parts of a brief. Indeed, the preliminary statement affords you the opportunity to concisely and persuasively explain why you should win, and thus make an excellent first impression on the reader. Below are a few tips on how to draft a strong preliminary statement.

1.    Begin with a strong opening sentence that captures the reader’s attention.

            The first sentence in the opening paragraph of your preliminary statement should tell the court precisely and persuasively why you should win. Put differently, it should contain the theme of the case. Doing so will capture the court’s attention and focus the court’s attention immediately on the arguments that you believe support a ruling in your favor.  Be sure, however, not to draft an opening sentence that contains over-the-top language and unnecessary adjectives, that is excessively long, or that contains excess or esoteric words. Keep it simple and to the point. Consider the following examples:

“The defendant subjectively believed that her life was in danger when she used lethal force, and the decision to use such force was objectively reasonable.”

Versus

“This case is about the defense of self-defense, and the defendant should be found by this court to have exercised the defense of self-defense in this case.

            Of course, the first example is not perfect, but you get the point. The second sentence is an unmitigated disaster and will certainly not capture the judge’s attention (in a positive way) or begin your brief persuasively.

 2.    Tell the court what you want.

            In the first paragraph of your preliminary statement, inform the court of the relief that you are seeking. For example, if you are opposing a summary judgment motion, say, “The defendant’s motion for summary judgment should be denied,” or if you are the plaintiff moving for leave to file an emergent appeal, say, “The plaintiff’s motion for leave to file an emergent appeal should be granted.” It sounds simple – and it is – but it's important to let the court know at the outset what relief you are seeking.

 3.    Tell the court why you should get what you want.

            Explain to the court why you should get what you want. One strategy to ensure the effective organization and flow of your preliminary statement is to use the Rule of Two or the Rule of Three roadmap, in which you state concisely the two or three reasons that support ruling in your favor.  Doing so gives the court an outline of the arguments to expect in the brief and allows you to explain why those arguments are meritorious.  Consider the following examples:

 “The plaintiff’s defamation claim should be dismissed because the allegedly defamatory statements: (1) were substantially true; (2) constituted protected opinion; and (3) did not cause the plaintiff’s alleged harm.”

 Versus

“The plaintiff has alleged that the defendant defamed her, but that claim should be dismissed because, as discussed below, several defenses exist that prohibit the plaintiff from recovering damages in this matter.”

             The problem with the second sentence is that it doesn’t say anything, and it gives the court no indication of the arguments that you intend to rely on to support your position.

            Importantly, each paragraph that follows should be dedicated to explaining separately why each of the two or three reasons supports your position. 

4.    Be concise.

            Always be concise and get to the point, using simple language and, as a general matter, never exceeding three pages. As such, avoid, among other things, Latin, legalese, fancy “SAT” words, long sentences, adverbs, adjectives, over-the-top language, and unnecessary repetition. Using such language suggests that you are trying to artificially persuade the court and do not believe in the strength of your arguments. Consider the following examples:

“On December 1, 2022, a blizzard struck Hasbrouck Heights, New Jersey, a town of 15,000 residents, with accumulations of approximately twenty-two inches of snow. The defendant, Mike Smith, owned Mike’s Grocery Store, a popular destination for many Hasbrouck Heights residents. In the aftermath of the blizzard, and for approximately five days, Mike remained open but did not make any effort to clear the snow and ice that had accumulated in the parking lot and walkway. As a result, on December 3, 2022, as Barbara Johnson, an elderly woman and a frequent patron, was walking to the front door, she fell, suffering severe injuries, including a concussion and broken shoulder. Barbara’s injuries were the direct and proximate result of Mike’s negligent conduct and entitle Barbara to damages.”

Versus

“As discussed in more detail infra, on December 1, 2022, a shocking event occurred in Hasbrouck Heights, New Jersey that no one could have ever predicted or imagined. Almost two feet of snow fell and the deleterious effects on the town’s vulnerable residents were incalculable and incomprehensible. However, despite the undeniable dangers that the storm engendered, Barbara Johnson, an elderly and mercurial woman, make the fateful decision to risk her life by venturing to Mike's Grocery Store, where the parking lot was covered in snow and the deleterious conditions unquestionably apparent. Not surprisingly, Barbara fell while endeavoring to enter the store and suffered injuries that any reasonable person would have foreseen. As such, and as described infra, Barbara’s injuries are ipso facto the result of her negligence and the complaint should be dismissed.

            Again, the first example is not perfect, but the point should be obvious. The second example is about as bad as it gets.

5.    In most instances, do not cite cases in the preliminary statement.

            Some may disagree with this point, but in my view, the preliminary statement should provide a concise and compelling overview (and roadmap) of your arguments, including the facts that support granting the relief you seek. Citing cases can disrupt the flow and is arguably unnecessary because the legal argument section is where you will rely on case law to expand upon and further support your position.

***

       *For an additional and helpful discussion of the preliminary statement, see Jayne T. Woods' excellent post, dated May 9, 2023, titled "Should I include a stand-alone "introduction" section in my brief?" 

May 28, 2023 in Appellate Advocacy, Appellate Practice, Appellate Procedure, Law School, Legal Profession, Legal Writing | Permalink | Comments (0)

Tuesday, May 9, 2023

Should I include a stand-alone “introduction” section in my brief?

I was recently discussing persuasive writing with an appellate attorney, and he mentioned how important he believed the “introduction” section of the brief was.  He wasn’t talking about an introductory paragraph to the argument; he meant an entirely independent, stand-alone section of the brief. 

The idea of an “introduction” (or preliminary statement) section has taken hold over the past few years in the appellate practice world.  It was mentioned on this very blog back in 2019:  https://lawprofessors.typepad.com/appellate_advocacy/2019/12/writing-an-outstanding-appellate-brief.html. But those who support it also recognize that not all appellate courts authorize it.[1]  And that raises several questions.

  • What is an “introduction” section?

An introduction section has been described by advocates as “a short and persuasive overview of the case,”[2] or “a concise statement of the issues and arguments that the writer view[s] as most important, as well as the desired outcome.”[3]  

While most appellate courts do not expressly authorize its inclusion in briefs, some do.  Arizona, Illinois, Kentucky, Maine, Minnesota, Utah, and Washington all expressly authorize (or require) an introduction section in their state appellate court rules.[4]  Utah’s rule says that “[t]he introduction should describe the nature and context of the dispute and explain why the party should prevail on appeal,” while the Illinois rule provides a model:  “This action was brought to recover damages occasioned by the alleged negligence of the defendant in driving his automobile. The jury rendered a verdict for the plaintiff upon which the court entered the judgment from which this appeal is taken. No questions are raised on the pleadings.”[5]  But the other state rules provide less guidance, suggesting that the introduction should address the “nature of the case” (Kentucky and Maine) or be “concise” (Washington), while Arizona and Minnesota provide no guidance at all.

With respect to the federal circuits, none address introductions in their local rules, but Westlaw’s Practical Law toolkits suggest that introductions are commonly included by practitioners in the First, Second, Fifth, Eleventh, and Federal Circuits.  These introductions are generally described as “a short preliminary explanation of the facts and procedural history of the case [with an] expla[nation] why the . . . Circuit should grant the appellant relief from the district court’s order or judgment.”[6]

  • What are the pros and cons of using an introduction?

As with any persuasive writing, you must first know your audience.  As a law clerk, I’ve seen only a few of these (they are not expressly authorized by my state’s rules), and I was neither put off nor blown away.  For me, it was meh.  But it’s really the judges’ opinions that matter, so I asked the judge I work for if she had noticed them and what she thought.  She also expressed mixed feelings, noting that introductions were helpful only if they were well-written, avoided redundancy, were brief, and acted as a guide for analyzing the claims on appeal.[7]

There are several potential benefits from a well-written introduction section.  You get to frame the case; you get to prime your reader to accept your legal positions or view the facts favorably to your claims;[8] and you can help the court navigate your brief.

But there are risks, as well.  The most obvious is potential redundancy.  Most appellate courts permit or require a summary of the argument section.  According to the federal rules, this section “must contain a succinct, clear, and accurate statement of the arguments made in the body of the brief, and . . . not merely repeat the argument headings.”[9] And, presuming your argument identifies the nature and context of the dispute and explains why your client should prevail, it’s hard to see the distinction between the summary of the argument and an introduction.  As one author put it, “At best, the brief simply contains two summaries of the argument, rather than one.”[10]  And one Florida court noted, “Outlines of substantive arguments are more proper in a brief's summary of argument section.”[11]

An additional (and very real) risk is violating a procedural rule.  Most appellate courts allow for dismissal of appeals in the face of briefing rule violations.  Even in jurisdictions allowing introductions, failing to write them properly (or taking liberties with the opportunity) can land you in a court’s crosshairs.  See, e.g., Yakima Sch. Dist. No. 7 v. Magee, 16 Wash. App. 2d 1079 (Wash. App. Div. 3 2021) (rejecting the appellant’s “preamble” as “a confusing jumble of words” that failed to “help the court or opposing counsel ‘expeditiously review’ the issues in the case”).  Furthermore, in jurisdictions without express rules, it is unclear whether an introduction counts in the page and word limits or whether the failure to include legal or record citations constitutes a violation of other briefing requirements.  And both the Second Circuit and the United States Supreme Court have rules requiring briefs to be free of “irrelevant” or “immaterial” matter.[12]

In short, the inclusion of an optional or unauthorized introduction is a gamble with some significant risk for potentially high reward—but only if it is done well.

  • How do I effectively use an introduction?

The first decision is where to put it.  Its name, alone, suggests it should appear near the beginning of the brief, and jurisdictions with express rules generally say it should appear immediately after the table of authorities.[13]  In federal circuits where common practice exists, introductions appear immediately after the table of authorities (First and Second Circuits), after the statement of issues presented (Fifth Circuit), or between the statement of related cases and the jurisdictional statement (Federal Circuit).  Common practice in the Eleventh Circuit appears variable, with some introductions appearing at the very beginning, some after the table of authorities, and some as the first heading in the statement of the case.  (Though it seems odd to include the introduction within the statement of the case, the reason for doing so may be logistical; some appellate judges rely on summaries provided by staff attorneys, and including the introduction in the statement of case increases the likelihood that it will be included in those summaries.  Of course, placing the introduction within the statement of case may also increase the likelihood of a rules violation if the introduction lacks citation or includes argument.)[14]

The next decision is whether to include citations to either the record or legal authority.  In Washington, “[t]he introduction need not contain citations to the record or authority.”[15]  And judges who are open to introductions generally suggest that citations in this section detract from its purpose and effectiveness.  But, as mentioned above, whether you are required to include record citations depends to some degree on location of your introduction, and many appellate courts require citations to the record for every factual assertion in the brief.[16]

Additional considerations are whether introductions are appropriate in every case and, if included, how long they should be.  Considering how judges and law clerks use introductions, they are most effective when included in complex cases and least effective in simpler ones.  And there is universal agreement that they must be brief and concise or risk being ignored.  Thus, one author suggests, “Where introductions are concerned, you should make sure that every single word counts.”[17] 

As for contents, begin by describing the type of case (e.g., premises liability, landlord/tenant dispute, employment discrimination) and then provide a roadmap (as opposed to a summary) for the main arguments.  “This roadmap should say, in basic terms: what happened; what law applies; and what the result should be.”[18]  Here’s an example from a brief in the Eleventh Circuit:

This is a dispute regarding insurance coverage. [Insured] lived at Lakeview apartments. She sued Lakeview after she slipped and fell on a leak when the “air conditioning units” at the apartments stopped working. At issue is whether a Water Related Exclusion, which precludes coverage for bodily injuries arising out of, related to, or in any way involving a discharge or leak from “appliances,” applies to [Insured’s] lawsuit against Lakeview.

[Insurer’s] position is it does not have a duty to defend because [Insured] clearly alleges her bodily injuries arise out of a leak from an appliance, i.e., the air conditioning units. While the word “appliance” is not defined in the Policy, its ordinary meaning is a “device for a particular use or function.” An air conditioning unit meets this definition; simply, it is a device used to heat or cool air. There is no coverage under the terms of the Policy.

The district court disagreed and concluded [Insurer] has a duty to defend because it is not clear whether an HVAC system is an appliance. In the district court's view, an “appliance” means something “that you plug in, like a dishwasher or refrigerator.” The district court appears to have been swayed by Lakeview's expert who opined that the word “appliance” does not mean a building's HVAC system.

Applying the ordinary definition of “appliance” it is clear the Water Related Exclusion applies to the allegations in [Insured’] complaint. Moreover, expert opinion is irrelevant to the duty to defend. See Selective Ins. Co. v. William P. White Racing Stables, 718 Fed. Appx. 864 (11th Cir. 2017). This Court should reverse.[19]

The Takeaways:

  • Check your local rules first to see if introductions are authorized, and if so, whether there are any requirements or constraints on usage;
  • Use introductions for only complex cases where they can be a helpful guide for your reader;
  • Ensure you are complying with other briefing requirements (e.g., record references and word/page limits); and
  • Be concise—limit yourself to one page at most.[20]

*For more detailed advice on drafting effective preliminary statements, check out Adam Lamparello's recent post:  https://lawprofessors.typepad.com/appellate_advocacy/2023/05/drafting-a-strong-preliminary-statement.html

 

[1] See, e.g., Chris W. Altenbernd, Legalizing the Appellate Introduction, 90 Fla. Bar J. 60 (Sept./Oct. 2016), available at https://www.floridabar.org/the-florida-bar-journal/legalizing-the-appellate-introduction/.

[2] Savannah Blackwell, Legal Writing Tip:  Start Your Brief With a Solid Introduction, available at https://www.sfbar.org/blog/legal-writing-tip-start-your-brief-with-a-solid-introduction/

[3] Lance Curry, No Introduction Needed?  The Effectiveness of Introductions in Appellate Briefs, The Record, Journal of the Appellate Practice Section of the Florida Bar (Winter 2011), available at http://therecord.flabarappellate.org/wp-content/uploads/2018/07/AP-Winter-11.pdf.

[4] See Ariz. R. Civ. App. P. 13(a)(3); Ill. Sup. Ct. R. 341(h)(2); Ky. R. App. P. 32(A)(1); Me. R. App. P. 7A(a)(1)(C); Minn. R. Civ. App. P. 128.02.1(d); Utah R. App. P. 24(a)(4); Wash. R. App. P. 10.3(a)(3). 

[5] According to Illinois law, “The introductory paragraph should not include lengthy recitations of fact and should not contain argument.”  Slater v. Illinois Lab. Rel. Bd., Loc. Panel, 144 N.E.3d 618, 624 (Ill. Ct. App. 1st Dist. 2019).  Thus, it is probably not the kind of introduction most advocates envision.

[6] See, e.g., Fifth Circuit Appellant's Brief, Practical Law Standard Document w-000-5018.

[7] These views have been echoed by other appellate judges, though some believe the introduction (if not expressly authorized by rule) is not only a waste of time but also a violation of appellate briefing rules.  Curry, supra note 3.

[8] Joe Regalia, Eight Easy Strategies to Write Better Introductions, available at https://write.law/blog/eight-simple-strategies-to-write-better-introductions

[9] Fed. R. App. P. 28(a)(7).

[10] Altenbernd, supra note 1.

[11] Florida Second District Court of Appeal, PRACTICE PREFERENCES, pg. 4, available at www.2dca.org.   

[12] 2d Cir. R. 28.1(a); Sup. Ct. R. 24.6.

[13] See Ariz. R. Civ. App. P. 13(a)(3); Ill. Sup. Ct. R. 341(h)(2); Ky. R. App. P. 32(A)(1); Me. R. App. P. 7A(a)(1)(C); Minn. R. Civ. App. P. 128.02.1(d); Utah R. App. P. 24(a)(4); Wash. R. App. P. 10.3(a)(3).  But see Ky. R. App. P. 32(A)(1) (indicating the introduction should be the first section of the brief); Minn. R. Civ. App. P. 128.02.1(d) (indicating the introduction should appear between the facts and the argument sections).

[14] See Curry, supra note 3, pg. 13-14.

[15] Wash. R. App. P. 10.3(a)(3); but see Est. of Gilkey v. Gilkey, 11 Wash. App. 2d 1080 (Wash. App. Div. 1 2020) (unpublished) (stating, “we disregard factual statements not supported by the record in the introduction, just as we disregard them in other parts of a brief”).

[16] E.g., 3d Cir. R. 28.0(c) (“All assertions of fact in briefs must be supported by a specific reference to the record.”); 5th Cir. R. 28.2.2 (“Every assertion in briefs regarding matter in the record must be supported by a reference to the page number of the original record”); 6th Cir. R. 28(a) (“A brief must direct the court to the parts of the record it refers to.”); 9th Cir. R. 28-2.8 (“Every assertion in the briefs regarding matters in the record, except for undisputed facts offered only for general background, shall be supported by a citation to the Excerpts of Record”); 11th Cir. R. 28-1(i) (“In the statement of the case, as in all other sections of the brief, every assertion regarding matter in the record shall be supported by a reference to the record”) (emphasis added); Fed. Cir. R. 28(f) (“Any reference in a brief to the underlying record . . . must be to the corresponding appendix page number(s) assigned to the material”); D.C. Cir. R. 28(b) (“When citing to the record, authorities, or any other material, citations must refer to specific pages of the source”).

[17] Jon Barnes, Intro to Intros: How to Write the Winning Preliminary Statement, 58-APR Ariz. Att’y 28 (April 2022).

[18] Id.

[19] KINSALE INSURANCE COMPANY, Plaintiff-Appellant, v. LAKEVIEW TOWER VENTURE, LP, et. al., Defendant-Appellee., 2023 WL 1778409, at *1-2 (11th Cir. App. Br.).

[20] Federal practice suggests that one-to-two pages is an acceptable length, but some state court rules expressly limit introductions alone, or in combination with other sections, to one page.  See, e.g., Ky. R. App. P. 32(A)(1).

May 9, 2023 in Appellate Advocacy, Appellate Practice, Appellate Procedure, Federal Appeals Courts, Legal Writing | Permalink | Comments (3)

Tuesday, May 2, 2023

Legal Communication and Rhetoric: JALWD Turns 20

The journal, Legal Communication and Rhetoric: JALWD, (formerly the Journal of the Association of Legal Writing Directors) will publish its twentieth volume this year. The journal has this mission statement:

The journal is dedicated to encouraging and publishing scholarship (1) focusing on the substance and doctrine of legal writing. Legal writing is broadly defined to include many types of writing in a lawyering setting; (2) grounded in legal doctrine, empirical research, or interdisciplinary theory; and (3) accessible, helpful and interesting to all “do-ers” of legal writing: attorneys, judges, law students, and legal academicians. Published articles are intended to reach all of those audiences.[1]

The journal regularly includes articles that appellate practitioners will found helpful and it publishes articles written by practitioners as well as academics. Here are just a few examples:

  • Raffi Melkonian, Thoughts and Worries About Appellate Practice Post-Pandemic, 19 Legal Commc’n & Rhetoric 129 (2022)
  • Stephen Boscolo, Using Judicial Motives to Persuade Judges: A Dramatistic Analysis of the Petitioners’ Brief in Lawrence v. Texas, 17 Legal Commc’n & Rhetoric 103 (2020)
  • Scott Fraley, A Primer on Essential Classical Rhetoric for Practicing Attorneys, 14 Legal Commc’n & Rhetoric 99 (2017)
  • Barbara K. Gotthelf, The Lawyer’s Guide to Um, 11 Legal Commc’n & Rhetoric 1 (2014)
  • Stacy Rogers Sharp, Crafting Responses to Counterarguments: Learning from the Swing-Vote Cases, 10 Legal Commc’n & Rhetoric 201 (2013)
  • Scott Fraley, A Primer on Essential Classical Rhetoric for Practicing Attorneys, 14 Legal Commc’n & Rhetoric 99 (2017)

You’ll find a complete archive of the journal here Legal Communication & Rhetoric: JALWD

 

[1] https://www.alwd.org/aboutlcr

May 2, 2023 in Appellate Advocacy, Appellate Practice, Federal Appeals Courts, Legal Profession, Legal Writing, Oral Argument, Rhetoric, State Appeals Courts | Permalink | Comments (0)

Sunday, April 30, 2023

Succeeding in the 1L Year

Recently, several of my undergraduate students who are attending law school next semester expressed anxiety and uncertainty about the first year. Certainly, these feelings are normal and shared by many incoming first-year law students. But this need not be the case. Below is the advice that I gave to my students as they prepare to enter law school.

1.    Don’t focus on succeeding in class; focus on succeeding on the exam.

In law schools, many professors use the Socratic Method, in which they question law students regarding, for example, the facts, holdings, and reasoning of particular cases.  Many incoming law students fear the Socratic Method, worrying that they will embarrass themselves in front of the class. As such, these students often spend hours preparing for class and briefing cases.

That is the wrong approach.

At the overwhelmingly majority of law schools, your performance in class means absolutely nothing. Quite frankly, none of your fellow students care about how you perform in class. They are just relieved that they weren’t the one that the professor called on. Furthermore, don’t be impressed by the “gunners,” namely, those who talk excessively in class or ask what may appear to be incisive questions. They usually do not get the best grades – or even good grades.  And your grades and class ranking, not your performance in class, are, by far, the most important factor in determining your job prospects upon graduation.

This doesn’t mean, of course, that you shouldn’t be prepared for class. But you should be aiming for a merely average, not an exceptional performance because your time should be dedicated to far more important matters.

Specifically, from day one, you should be focused on preparing for the final examination, which in most law school’s doctrinal courses determines your final grade.

How do you do that?

First, learn how to take a law school exam. To do so, purchase the Legal Essay and Essay Writing primer, which is available at www.leews.com. This program will teach you how to draft an effectively organized and persuasively presented answer. It will teach you CRAC or, as some professors prefer, IRAC, which will ensure that your answer is structured properly. 

Second, take practice exams – under timed conditions. Doing so will simulate what you will face when taking the final exam and, ultimately, maximize your chance of obtaining a high grade. Additionally, review model answers to those exams, including those written and graded by your professor, to learn what constitutes an outstanding answer.

Third, don’t brief cases. Instead, purchase commercial outlines and other instructional materials, such as Emmanuel’s Law School Outlines and Joseph Glannon’s Civil Procedure coursebook. Why? Because you need to identify the relevant rules of law that govern the resolution of particular legal disputes, and because you need to know how to apply those rules to the novel fact pattern that a final examination will present. In other words, the facts of the cases you read during the semester are ultimately irrelevant. Thus, briefing those cases is an unnecessary waste of time.

Fourth, draft an outline that concisely summarizes the legal rules for each topic that you have studied. Do not draft a 120-page outline that summarizes the facts and holdings of every case. Rather, draft a twenty-page outline that contains only the relevant legal rules because those rules are what you will need to know for the final exam.

To summarize:

  • Don’t worry about how you perform in class.
  • Purchase the Legal Essay and Essay Writing primer.
  • Take practice exams.
  • Don’t brief cases.
  • Purchase commercial outlines.
  • Draft your own outlines.

Now, many law professors will tell you the opposite in law school. They may tell you, for example, not to purchase commercial outlines. Don’t fall for it. If you follow the approach outlined above, you will improve your critical thinking skills and maximize your chances of success in the first year.

2.    Membership on Law Review (or at least a law journal) matters to employers.

At many law schools, law review membership is typically reserved for students who graduate in the top 10% of their class after the first year or who gain membership through other means, such as a writing competition.

To be sure, employers value law review membership because it signals to them that the applicant is a high-quality student. Thus, strive for membership on your law review or, at least, on a specialized journal at your law school.

3.    Improve your writing and critical thinking skills.

Excellent writers and critical thinkers make excellent lawyers. From day one, focus on developing your persuasive writing skills and focus on gaining experience in drafting the most common litigation and transactional documents. Law firms and clients value immeasurably graduates who can write persuasively and whose analytical skills are second to none.

4.    Develop relationships with your peers and professors.

Employers are not simply looking for quality law school graduates. They want to hire good people. No one likes a jerk, an unbearable narcissist, or someone who just can’t seem to shut up.

Put simply, your reputation is critical to your success.

As such, conduct yourself with class. Be honest. Be nice. Have integrity. Support your classmates. Listen more than you talk. Don’t gossip. Don’t base your self-esteem on what grade you received in Torts. And realize that there is so much more to life than the law.

Additionally, get to know your professors. Schedule an appointment with them during their office hours to introduce yourself, to receive feedback on an assignment, or to ask questions about the practice of law. Most importantly, if you need help, ask for it.   

5.    Develop a strong mindset.

In law school, there will be times when you will fail. There will be times when you fail to live up to your expectations. And there may be times when, as in life, you experience unfairness.

But that does not determine your destiny. Failure is a good thing because it enables you to learn lessons that will enhance your growth as a lawyer and as a person. Not meeting your expectations can teach you what you need to do differently in the future to achieve the result you desire. And unfairness can teach you the value of justice.

Indeed, your choices, not your circumstances, determine your destiny; how you respond to adversity is critical to whether you achieve failure or success. Put simply, how you think impacts what you believe and, ultimately, what you do.

So be sure to focus on both your professional and personal development in law school. Doing so will enable you to be successful -- and happy.

April 30, 2023 in Law School, Legal Profession, Legal Writing | Permalink | Comments (0)

Saturday, April 22, 2023

Comments Against Angel Reese Call Us to Check for Bias in Our Writing

As I’ve mentioned before, I was lucky enough to teach a seminar on bias in legal analysis and writing this semester.  Much of the class focused on implicit bias and the way we can use words as lawyers to help find and remove bias.  Occasionally, we encountered bias in court opinions, legal scholarship, and the like that was almost express.  While easier to spot and remove than subtle implicit bias, overt bias also reminds us, as lawyers and legal writers, to scrutinize our own writing. 

One example of clear bias in the media that could help us as legal writers came at the end of the NCAA basketball tournament this year.  Students and I were struck by social media and sportscaster disparate discussion of a strong, powerful player for the University of Iowa and a strong, powerful player for Louisiana State University.  These women, Angel Reese of LSU and Caitlin Clark of Iowa, are incredible competitors who each led their teams to the NCAA championship game.  Along the way to the final game against each other, which LSU won, both played beautifully and both sported almost identical ponytails.  Both also made the same “you can’t see me” taunt to opponents during the tournament by waving their outstretched hands in front of their faces, to show they were too quick for opponents to see and stop.  In response to these taunts, Clark faced praise, including from ESPN and pro wrestler John Cena, who invented the “you can’t see me” taunt, but Reese faced profanities and statements she was “classless.”   

The difference:  Clark is white, while Reese is Black.  Our class had a robust discussion of what the different language used to describe these similar athletes using identical taunts in the same tournament meant to us as legal writers, and the students inspired me to share this incident here.

As Mike Freeman of USA Today explained, “Clark is a skilled trash talker and used the John Cena "you can't see me" taunt multiple times throughout the tournament.” Mike Freeman, Reaction to Angel Reese taunting Caitlin Clark shows the double standard for Black Athletes,  https://www.usatoday.com/story/sports/columnist/mike-freeman/2023/04/03/angel-reeses-taunt-iowas-caitlin-clark-shows-double-standard/11591498002/ (Apr. 3, 2023).  Freeman continued, “[i]n the closing moment of the championship game, Reese did the same taunt and also pointed to her hand, signaling she was getting a championship ring.”  Id.   

Aisha Sultan of the St. Louis Post-Dispatch noted Clark often taunted opponents.  Sultan explained:  the “you can’t see me,” gesture “had been used by Clark toward a Louisville opponent in the Elite Eight” round of the NCAA tournament, and “ESPN even produced a segment hailing Clark as the “Queen of Clapbacks” featuring these moments of taunting by her.” Aisha Sultan, Backlash to Angel Reese raises question: Which athletes get called 'classless'?, https://www.stltoday.com/lifestyles/parenting/aisha-sultan/sultan-backlash-to-angel-reese-raises-question-which-athletes-get-called-classless/article_fa75a30d-67d7-56c1-aac6-ea09c00b638f.html (Apr. 3, 2023).  “The reaction to Reese [using the taunt in the final game], however, included Dave Portnoy, founder of the site Barstool Sports, tweeting that she was a ‘classless piece of (expletive)’ and Keith Olbermann calling her an ‘(expletive) idiot’ on Twitter.”  Id.

Freeman honed in on the use of language here, and his notes are especially helpful to appellate writers as we edit our work.  For example, he described what he called stereotypes of sports as:

When Black players are aggressive, and talk trash, they are thugs and animals.

When white players are aggressive, and talk trash, they are passionate and fiery.

This stereotype goes back decades. Larry Bird was the greatest trash talker of all time but was celebrated for his passion. Tom Brady screamed at teammates and coaches and was viewed as scrappy. John Thompson's Georgetown Hoyas, who played defense with spirit and ferocity, were called thugs. Fight[ing] in hockey is seen as tradition. Fight[ing] in NASCAR is seen as cool and spirited. Fights in NBA games lead to white commentators asking: "Where are the fathers?"

https://www.usatoday.com/story/sports/columnist/mike-freeman/2023/04/03/angel-reeses-taunt-iowas-caitlin-clark-shows-double-standard/11591498002/

What can we learn from this incident to catch less obvious bias in our own writing?  The long answer: my class spent fourteen weeks looking at scholarship on writing and bias to help us start to answer this question, and removing bias takes work and careful attention.  One shorter answer:  many of the rules of good writing, like using active voice and direct sentence structure, help us avoid bias.  Being attentive to our own underlying privilege and bias and asking a trusted colleague to proofread helps too.  There are many thoughtful ideas on addressing bias in our legal publications.  For just a few, consider recent articles, like I Think He’s Nice But He Might Be Mad About Something, 25 U.C. Davis Soc. J. L. Rev. 73, 99 (2021), and older scholarship, like Prof. Lucinda Finley’s Breaking Women’s Silence in Law:  The Dilemma of the Gendered Nature of Legal Reasoning, 64 Notre Dame L. Rev. 886, 886-97, 909 (1989).

I give this example of overt bias in sports discussions not as a suggestion appellate lawyers often show such bias, but as a reminder we all must be as thoughtful as possible in the words we choose.  My students helped me see we should all take the time to edit for bias when we check for clarity and punctuation, and we should mentor new appellate writers to do the same.

April 22, 2023 in Appellate Advocacy, Appellate Court Reform, Appellate Justice, Appellate Practice, Current Affairs, Legal Ethics, Legal Profession, Legal Writing | Permalink | Comments (0)

Thursday, April 6, 2023

Prompt Engineering for ChatGPT Can Improve Your Legal Writing—Even if You Never Use ChatGPT

Thursday’s Rhaw Bar: A Little Bite of All Things Rhetoric and Law—exploring ideas, theories, strategies, techniques, and critiques at the intersection of rhetoric and legal communication.

Prompt Engineering for ChatGPT Can Improve Your Legal Writing—Even if You Never Use ChatGPT

Generative artificial intelligence (AI), like ChatGPT and Bing’s AI-powered chat, is motivating a fundamental reconsideration of the ethics and practicalities of how humans can produce good writing.  In the legal writing context, there’s plenty of discussion around whether and how legal writers should use generative AI as part of writing practice.  While I’m not going to delve into the questions about whether and how to best use generative AI like ChatGPT in legal writing (I’ve already done a little bit of that here), I want to look at a skill necessary for working effectively with generative AI that I think can help you be a better writer in general:  prompt engineering or prompt design.   Understanding prompt engineering and applying it to your own writing can help you write better.

What is Prompt Engineering?

Prompt engineering is the process of using specific words and phrases along with choices about the structure and organization of those words and phrases to write instructions that improve generative AI’s ability to provide a response that is useful to a human prompter.  The emerging literature around generative AI suggests that prompt engineering will be a skill that writers will need to competently use large language models like ChatGPT. 

Prompting for ChatGPT is done in natural language, in everyday conversational English (for English speakers). This is because ChatGPT is trained to understand and respond to conversation in a conversational manner.  So no specialized programming knowledge is needed to prompt ChatGPT;  instead, a human prompter needs two things:  (1) an understanding the rhetorical situation to which ChatGPT is being asked to respond, and (2) an ability to communicate that rhetorical situation precisely and clearly to ChatGPT in everyday language.

Prompt Engineering and the Rhetorical Situation

Prompt engineering, at bottom, represents a human ability to carefully describe rhetorical situations that call for some kind of communicative response.  In other words, prompts give ChatGPT a way to get to know the rhetorical situation confronting the human prompter, which includes the needs of the audience, the limitations and opportunities presented by the context, and the purpose of the writing in relation to the issues confronted by the writer. Like all other writing, writing generated by ChatGPT is more effective if it is written specifically for the rhetorical situation the human writer envisions; that is, it is written for a specific audience, with a specific purpose, and in an appropriate tone.  The better engineered a prompt, the better chance there is of generating useful text appropriate for the rhetorical situation. 

An Example of the Basic Techniques of Prompt Engineering

Ultimately, prompt engineering is a set of techniques that encourage ChatGPT to generate more useful responses.  There’s quite a bit to know about prompt engineering, but reviewing the basic concept will help you understand how prompt engineering techniques can improve your own writing regardless of whether generative AI is part of the process.  Let’s walk through an example of how we might prompt ChatGPT to generate content about an appellate standard of review.

 “Write a paragraph that sets out the de novo standard of review.”

This is a basic prompt in the form of an instruction, and I used it to get this result from ChatGPT: 

The de novo standard of review is a legal standard applied by courts when reviewing decisions made by lower courts or administrative agencies. Under this standard, the reviewing court gives no deference to the decision made by the lower court or agency, and instead, conducts a completely fresh review of the evidence and legal arguments presented. This means that the reviewing court does not consider the lower court or agency's decision as binding or controlling and has the power to make an entirely new decision based on the evidence and arguments presented to it. The de novo standard of review is typically used in cases where there are no factual findings to be reviewed, or when the issue being reviewed is a question of law.

Not too bad, but through prompt engineering, I might generate a better result.  First, I can give ChatGPT context about the rhetorical situation, specifically describing the audience for whom it is writing: 

“You are writing an appellate brief for the United States Court of Appeals for the 11th Circuit.  Appellate court judges are your audience.”

I can also describe to ChatGPT the specific output I expect: 

“Write a paragraph that sets out the de novo standard for the standard of review section of the appellate brief.”  

So now, my more specific, detailed, and rhetorically aware prompt looks like this:

“You are writing an appellate brief for the United States Court of Appeals for the 11th Circuit.  Appellate court judges are your audience. Write a paragraph that sets out the de novo standard for the standard of review section of the appellate brief.”

In this prompt, I've added more information about the rhetorical situation for ChatGPT to draw upon as it attempts to predict the best response for the prompt.  (Remember, ChatGPT and other generative AI predict what words are appropriate in response to the prompt; they do not think, analyze, or evaluate, they predict using mathematical models for language). 

This was the response to my new prompt:

In this appellate brief, we are appealing a decision made by a lower court to the United States Court of Appeals for the 11th Circuit. As appellate court judges will be our audience, it is important to explain the standard of review that will be applied in this case. Under the de novo standard of review, the appellate court will review the lower court's decision without giving any deference to the lower court's findings or legal conclusions. The appellate court will instead conduct a fresh review of the record and make its own determination as to the appropriate legal outcome. This standard of review is typically applied in cases where the lower court's decision involved purely legal issues or when there were no factual findings made by the lower court. In this case, we argue that the de novo standard of review should be applied to our appeal.

Two notable things happened here. First, expert legal writers will recognize stylistic junk in the response.  Specifically, a clumsy first sentence, an explicit nod to judges as the audience, and a specific statement that it is important to identify the standard of review are all stylistically awkward choices for an appellate brief.  But second, and more favorably, experts will recognize that ChatGPT generated a response that is more rhetorically aware:  it generated a response that is less academic in its tone and is written from the point of view of the appellant. While the voice of the paragraph needs more attention in revision, ChatGPT has improved the rhetorical sensibility of the response.

But I think I can get ChatGPT to do better.

Rather than having ChatGPT start over with a new paragraph, I’m going to give it a chance to revise the existing paragraph.  I will ask ChatGPT to revise what it wrote, and I will give it more detailed information about the rhetorical situation (in other words, I will add more input data for it to work with in generating a response).  I’ll tell ChatGPT that I am dealing with an appeal from summary judgment and that I’d like some case citations:

“Revise this paragraph to focus on the standard of de novo review for summary judgment motions.  Add citations to cases from the United States Court of Appeals for the Eleventh Circuit that support the assertions in the paragraph.”

Here’s the response:

In the United States Court of Appeals for the Eleventh Circuit, the standard of review for summary judgment motions is de novo. This means that the appellate court will review the lower court's decision on summary judgment without any deference to the lower court's findings or legal conclusions. The appellate court will conduct a fresh review of the record to determine whether there are any genuine issues of material fact and whether the moving party is entitled to judgment as a matter of law. As stated in Gil v. Winn-Dixie Stores, Inc., 257 F.3d 1258 (11th Cir. 2001), "we review a grant of summary judgment de novo, applying the same legal standards as the district court and viewing the evidence in the light most favorable to the nonmoving party." Similarly, in Rice-Lamar v. City of Fort Lauderdale, 232 F.3d 836 (11th Cir. 2000), the Eleventh Circuit held that "we review the grant of summary judgment de novo, drawing all inferences in favor of the nonmoving party." Therefore, we ask the appellate court to apply the de novo standard of review in this case to ensure a fair and impartial review of the lower court's decision on summary judgment.

A good appellate writer will recognize that there’s still some stylistic awkwardness in this paragraph that can be eliminated with some revision.  For example, the paragraph can be made more concise by eliminating the quoted material from the case law and instead using the citations provided (assuming they are accurate—accuracy cannot be assumed with ChatGPT) to support the first three sentences of the paragraph. But what is good about the paragraph is that its detail, point-of-view, and tone are more tailored to the rhetorical situation confronting the appellate writer, and the paragraph is responsive to the human prompter’s details. At minimum, there is more richness in the content that the human drafter can use to write  an effective statement of the standard of review.

In sum, three ideas about writing emerge from our prompt engineering example:

  • Good writing depends on the writer’s ability to carefully interrogate and explicitly articulate the features of the rhetorical situation.
  • Being able to identify and articulate the specific writing task to be performed, the context for that task, the details of that context, and the output to be generated can improve the chances of writing to effectively respond to the rhetorical situation.
  • Prompt engineering can improve the process of making targeted, thoughtful, and specific revisions.

Using Prompt Engineering in Your Own Writing (and in Mentoring Others’ Writing)

Even if a legal writer never uses a tool like ChatGPT to generate text, using the techniques of prompt engineering in the writing process can help legal writers write better.

It’s likely true that experts in appellate writing subconsciously generate prompts like those we’ve examined here, and those subconscious prompts guide their writing. But remember that ChatGPT got better at its task when it received explicitly stated, detailed prompts.  What might it look like to do the same thing in your own writing, to use prompt engineering as a conscious step?  And could prompt engineering help expert writers mentor inexperienced ones?

Here’s an example of how prompt engineering might help a more experienced writer mentor a more novice one.

Imagine this case. A school district disciplines a high school student for refusing to participate in a school assembly honoring Veteran’s Day.  The student asserts a political motive for refusing to participate and that the discipline violates her free speech rights.  Both the school district and the student move for summary judgment before the trial court.  The court grants summary judgment for the school district and denies it for the student.  The student’s lawyers, one senior appellate lawyer and one junior one, are working together on the appeal, arguing that, as a matter of law, the trial court decided the cross-motions incorrectly.

The junior lawyer has written the first draft of the brief, but the senior lawyer has found it lacking in persuasiveness, particularly because the junior lawyer has not been effective in supporting her argument with factually analogous cases that have outcomes favorable to the student’s position.

In guiding the junior lawyer’s revisions (whether in conversation or in writing), the senior lawyer could use prompt engineering techniques.  The senior lawyer could give the junior a basic instruction like “Improve the quality of the analogies in the arguments.”  But engineering that prompt could yield better results. First, a better instruction would clarify the task: “Add to the argument analogies to cases that are factually similar and support the outcome we seek.”

Then the prompt would include context that helps the junior lawyer see the rhetorical situation more clearly and from the point of view of the more experienced lawyer.  For example, the senior lawyer could add:

“The judges will find analogies to cases persuasive.  Cases where an appellate court has reversed summary judgment on similar facts are good for analogies. Ideally, you want to draw the court’s attention to cases where a student was silent or absent from a required school activity and asserted a political reason and the court thought the student was entitled to summary judgment.”

Even further, a good prompt from the senior lawyer could include the output expectation:  “Revise your argument paragraphs to add comparisons to at least two cases (if you can find them) that are analogous on their facts and favorable on their outcome.  Be specific about the analogies—use details to show how the cases are similar to our case.”

So, what’s going on here?  We’ve engineered a prompt—from senior lawyer to junior one—that is more likely to yield what the senior lawyer knows will be more effective argument in the appellate brief. It includes detailed instructions, input data about useful analogies, audience information, and clear output instructions.

While this example reflects communicating a prompt between two people, you can be your own audience for a prompt.  Before beginning a project,  you might write a prompt that will guide the drafting. In addition, when you are struggling with a particular part of a document, you might stop and ask, “What is my prompt for writing this?”  “What instructions do I give myself here?  What is the context, the audience, the purpose?  What is the output I’m seeking?”  You might even take a moment and write that prompt down to focus your efforts.  By using the techniques of prompt engineering, you can slow down the process and explicitly analyze the rhetorical situation, which can improve the output.

The Recap

Prompt engineering is a useful technique for working with generative AI because prompt engineering can improve the quality of the responses generated.  But prompt engineering can also be a useful technique for legal writers more generally because prompting forces writers to carefully articulate the demands of the rhetorical situation and define precisely what response to that situation is appropriate.  The prompt engineering method of creating precise writing instructions, contextualizing those instructions with detail about rhetorical situation, and describing the desired output can help a writer generate text, revise existing text, or give good feedback to other writers.  Prompt engineering can help with writing and revision at all levels, from drafting the entire document to the revision of sentences.

Kirsten Davis teaches at Stetson University College of Law and in the Tampa Bay region of Florida. She is the Co-Director of the Institute for the Advancement of Legal Communication. The Institute’s mission is to study legal communication issues and provide programming and training that improves legal communication skills. Among other things she’s up to right now, she’s currently working on a writing handbook written specifically for trial lawyers. The views she expresses here are solely her own and not intended to be legal advice. You can reach Dr. Davis at [email protected].

April 6, 2023 in Appellate Practice, Legal Profession, Legal Writing, Rhetoric | Permalink | Comments (0)

Saturday, March 25, 2023

Revisiting George Orwell and Good Writing

This semester, I am lucky enough to be teaching a seminar I designed on bias in legal analysis and writing.  The class has been a delight, and I am impressed every week by my thoughtful and dedicated students. 

In one of our sessions, I proposed using George Orwell’s writing rules, along with his broader concerns with “Doublespeak” and “Big Brother,” to add clarity and remove bias from writing.  Several of my students have included these ideas in the class papers they are drafting, and I hope these tips help you draft as well.

In his pre-1984 essay, Politics and the English Language, Orwell proposed six rules on using English, and he repeated these in later works as well.  Many commentators have discussed using the rules for clarity, but I believe we can also combat bias with these ideas.

Here are Orwell’s rules, as summarized by Judith Fischer in her article Why George Orwell’s Ideas About Language Still Matter for Lawyers, 68 Mont. L. Rev. 129, 135 (2007): 

(i) Never use a metaphor, simile or other figure of speech which you are used to seeing in print.

(ii) Never use a long word where a short one will do.

(iii) If it is possible to cut a word out, always cut it out.

(iv) Never use the passive where you can use the active.

(v) Never use a foreign phrase, a scientific word or a jargon word if you can think of an everyday English equivalent.

(vi) Break any of these rules sooner than say anything outright barbarous.

See also Austin Wayne Schiess, Writing a Brief the George Orwell Way, 14 App. Advoc. 6, 6-6 (2001). 

How can we use these rules in appellate writing?  

  1. Avoid Cliches. Fischer notes: “Think out of the box” and “avoid cliches like the plague.” 68 Mont. L. Rev. at 137.  But seriously, some cliches are racist and many are unclear.  Remove them from your writing as much as possible.
  1. Prefer Shorter Words. I am old enough to remember when courts imposed motion and brief page limits, long before word limits. I recommend reading your own work as if you have page limits and word limits.  This can help you remove legalese, redundant wording, and unneeded long terms.  In his blog, Demian Farnworth suggests practicing by using only monosyllabic words.  The monosyllabic approach can add many words and decrease clearness, but it is a fun way to practice writing with shorter terms.  See https://copyblogger.com/short-sentences/ (Oct. 19, 2015).

3. Be Concise & 5. Avoid Jargon. (I’ve already blogged about Rule 4, Use Active Voice, often.) Use concision as an enemy of bias and obfuscation.  As Justice Ginsburg reminded us, our readers “simply don’t have time to ferret out one bright idea buried in too long a sentence.”  Remarks on Appellate Advocacy, 50 S.C. L. Rev. at 567 (1999).  One way to practice being concise and removing jargon is by reviewing any manual for a small appliance in your home.  Review these manuals for lengthy clauses and odd technical jargon.  My family’s favorite is our toaster manual, which often uses five words where one will do, and adds confusing technical details like “LED light indicator surround ring” for what is in fact the “toasting” light.  Finding these lengthy and confusing terms around the house will help you edit for concision in your briefing.

  1. Use Common Sense--Break Any of these Rules If they Reduce Clarity.  Recently, I learned there is reasonable debate about exactly what Winston Churchill said regarding ending a sentence in a preposition. Nonetheless, we know he said something close to:  “This is the sort of English up with which I will not put.”  See https://brians.wsu.edu/2016/11/14/churchill-on-prepositions/.  We can follow our own common sense, like Churchill and Orwell.  As another example, sometimes one longer clause reads better than a series of short, choppy sentences.  Let’s follow rules on clarity above all else.

Are these rules enough?  Orwell did not think so, as evidenced by his concern over “Doublespeak” and obfuscation.  To follow Orwell, therefore, we should make sure our words say what we mean.  While this sounds simple, any experienced appellate writer knows editing takes time and effort.  I hope Orwell’s rules help in this editing task.

March 25, 2023 in Appellate Advocacy, Appellate Practice, Books, Law School, Legal Ethics, Legal Profession, Legal Writing | Permalink | Comments (0)

Saturday, March 18, 2023

ChatGPT and Legal Writing

ChatGPT is an artificial intelligence chatbot that can, among other things, compose music, play games, and generate student essays and examination answers. Indeed, ChatGPT has already been studied to assess its efficacy on law school examinations. One study, for example, revealed that ChatGPT passed four law school exams at the University of Minnesota -- earning an average grade of C+ -- and an exam at the University of Pennsylvania’s Wharton School of Business.[1]

The leader of the study examining ChatGPT in the law school performance context stated that “[a]lone, ChatGPT would be a pretty mediocre law student," and emphasized that “the bigger potential for the profession here is that a lawyer could use ChatGPT to produce a rough first draft and just make their practice that much more effective.”[2]

Certainly, in law school and in the legal profession, ChatGPT can have benefits. For example, ChatGPT can enhance efficiency by, for example, producing rough drafts of basic legal documents such as complaints, memorandums, interrogatories, and document requests.  Additionally, ChatGPT can assist individuals who cannot afford legal services in producing competent legal documents.

What ChatGPT cannot do, however, is teach law students how to think, how to write, and how to persuade. That, in a nutshell, is the point – and the problem. Below are two concerns regarding ChatGPT’s effects on law school and the legal profession.

1.    Law students need to learn how to think critically.

Learning how to think critically is among the most important skills needed to be a competent lawyer. And in recent years, many students begin their first year of law school lacking this skill. Thus, during the first year of law school, particularly in doctrinal and legal writing courses, students learn, among other things, how to read cases, understand complex legal concepts, synthesize the law, and apply the law to different fact patterns.

ChatGPT is problematic because, in some contexts, it does the thinking for the students. In so doing, it enables students (to some extent) to avoid the admittedly arduous process of understanding and interpreting complex legal doctrines, and presenting such doctrines (e.g., in a memorandum or a brief) in an understandable, logical, and persuasive manner. Indeed, David Kemp, an adjunct professor at Rutgers Law School, stated that “[i]f you’re asking it to organize several concepts, or are struggling to explain something in a way that’s really understandable, it can help.”[3]

That, again, is the point – and the problem.

Students should not be relying on artificial intelligence to organize complex legal concepts or explain them in a way that readers can understand. They should, through hard work and perseverance, develop critical thinking skills so that they can do it themselves. Otherwise, we are training students to rely not on their minds or their legal training, but on a technology that, at best, produces mediocre results.

Perhaps some would describe this as an “old school” approach to legal education. And they would be right. The quality of law students at many law schools has steadily declined in recent years, and ChatGPT threatens to worsen this problem by doing for law students what they should, after three years of legal training, be able to do for themselves.

2.    Law students need to learn how to write competently and persuasively.

It is no secret that judges and lawyers often criticize law graduates for their poor writing skills.[4] The reasons for this include, but are not limited to, insufficient preparation during students' undergraduate coursework, and insufficient dedication to required legal writing courses in law school.

This fact, however, only underscores the need to train students to think – and write – like lawyers. Students need to learn, for example, how to research the law, how to craft a compelling narrative, how to synthesize legal authority, how to reconcile unfavorable facts and law, and how to draft an organized and well-structured legal argument.

To do so, students need to embrace the writing process, which involves writing, rewriting, and editing. It requires critical thinking. Hard work. Perseverance. And the ability to write effectively and persuasively. ChatGPT is not going to teach students how to do this because, at least to some extent, it will do it for them. That makes the problem worse, not better.

To be sure, ChatGPT may produce the equivalent of a mediocre first draft, which students will then edit and re-edit to improve its quality. But good legal writing is not simply about editing. To be an excellent editor, you must first be an excellent writer and re-writer. That means embracing the writing process and acquiring the skills needed to draft, for example, a persuasive motion or appellate brief. As one professor explains.

Legal writing faculty interviewed by the ABA Journal agree that ChatGPT writing can model good sentence structure and paragraph structure. However, some fear that it could detract from students learning good writing skills. ‘If students do not know how to produce their own well-written analysis, they will not pass the bar exam,’ says April Dawson, a professor and associate dean of technology and innovation at the North Carolina Central University School of Law.’[5]

Professor Dawson may be correct that ChatGPT will reduce bar passage rates. What it will almost certainly do is ensure that students never become excellent persuasive writers. And it will also cause some students to rely on ChatGPT to do the hard work that they should be doing, and that is necessary, to produce quality legal work.  This is the risk that reliance on ChatGPT – particularly for complex legal motions and briefs – engenders.

Ultimately, ChatGPT can certainly have benefits. Among those is increasing efficiency and productivity. But law students still need to have the analytical thinking and writing skills to be able to interpret complex legal texts, draft persuasive legal arguments, and present compelling arguments before a court.  As such, ChatGPT’s benefits must be balanced against the need to train students to think, write, and practice like lawyers.

Perhaps this is an “old school” approach, but that approach has produced extraordinary attorneys who have transformed the law and the legal profession through their advocacy.

Simply put, you cannot replace an intelligent, thinking human being.

 

[1] See Samantha Murphy Kelly, “Chat GPT Passes Exams from Law and Business Schools” (January 26, 2023), available at: ChatGPT passes exams from law and business schools | CNN Business

[2] Reuters, “Chat GPT Passes Law School Exams Despite ‘Mediocre’ Performance” (January 25, 2023) available at: ChatGPT passes law school exams despite 'mediocre' performance | Reuters.

[3] Kelly, supra note 1.

[4] See Ann Nowak, The Struggle with Basic Writing Skills (March 1, 2021), available at: The Struggle with Basic Writing Skills | Published in Legal Writing (legalwritingjournal.org)

[5] Kelly, supra note 1.

March 18, 2023 in Appellate Advocacy, Appellate Practice, Current Affairs, Law School, Legal Ethics, Legal Profession, Legal Writing, Rhetoric | Permalink | Comments (4)

Thursday, March 2, 2023

The Rhetoric of ChatGPT:  What ChatGPT Had to Say About Its Connection to Rhetoric and What We Can Learn from That Response

Thursday’s Rhaw Bar: A Little Bite of All Things Rhetoric and Law—exploring ideas, theories, strategies, techniques, and critiques at the intersection of rhetoric and legal communication.

The Rhetoric of ChatGPT:  What ChatGPT Had to Say About Its Connection to Rhetoric and What We Can Learn from That Response

I’ve been thinking about what ChatGPT might mean for the practice of appellate lawyers and their ability to be persuasive.  So, I typed this as a prompt for ChatGPT:

 I am writing a blog post for an audience of appellate lawyers. What should I tell them about the relationship between rhetoric and ChatGPT?

Here’s what ChatGPT replied:

Rhetoric is the art of using language effectively to persuade or influence an audience. In many ways, ChatGPT can be seen as an extension of this art, as it uses natural language processing to generate persuasive and compelling responses to a wide range of prompts.

One of the key advantages of using ChatGPT for rhetorical purposes is its ability to quickly generate high-quality content in a wide range of styles and formats. This can be particularly useful for appellate lawyers, who need to produce persuasive legal arguments and compelling briefs that are tailored to the specific needs of their clients.

At the same time, it's important to remember that ChatGPT is a machine learning model, and as such, it has limitations. While it can generate persuasive responses based on patterns it has learned from large volumes of text data, it cannot understand the nuances of human emotion, context, or intent in the same way that a human being can.

This means that appellate lawyers who use ChatGPT for rhetorical purposes must be careful to ensure that the responses generated by the model are appropriate and effective for their intended audience. They should also be aware that the use of ChatGPT in legal writing is still a relatively new and evolving area, and that best practices are still being developed.

Overall, ChatGPT can be a valuable tool for appellate lawyers looking to enhance their rhetorical skills and produce high-quality legal content. By using the model in conjunction with their own expertise and insights, lawyers can create persuasive and compelling arguments that effectively convey their clients' positions.

Analyzing ChatGPT’s Response

Not a bad response, generally speaking. But what has ChatGPT revealed about itself?  Here’s a brief analysis of some things we can learn about ChatGPT from this response.

            ChatGPT Might Assume Too Much About the Reader

ChatGPT starts with a correct definition of rhetoric and then asserts that ChatGPT is an extension of rhetoric because it uses natural language processing (NLP). But ChatGPT assumes the reader knows what NLP is.  (And later it assumes that the reader knows what a “language processing model” is.)   If you don’t know (I didn’t) what NLP is, here’s a quick definition sourced from IBM:

NLP combines computational linguistics—rule-based modeling of human language—with statistical, machine learning, and deep learning models. Together, these technologies enable computers to process human language in the form of text or voice data and to ‘understand’ its full meaning, complete with the speaker or writer’s intent and sentiment.

So, one thing we learn about ChatGPT from this passage is that it can wrongly assume a reader’s knowledge, something lawyers know better than to do. While we might think that better engineering of ChatGPT’s prompt would solve the problem, recall that I told ChatGPT the audience for whom I was writing. That specific detail in the prompt did not seem to make a difference in ChatGPT understanding that many members of the intended audience would have limited knowledge of the computer science terms associated with ChatGPT. 

            ChatGPT Thinks of Itself as “Art”

I’m intrigued that ChatGPT chose the term “art” when describing itself as an “extension” of rhetoric.  This characterization seems counterintuitive because ChatGPT is the product of computer, data, and language science.  Yet, ChatGPT suggests that because NLP is a human-like effort to understand the meaning of language (as the definition above reflects), ChatGPT sees itself as an “artistic” endeavor, at least regarding persuasion.  And, at least in some cases, ChatGPT has proven that to be true--there’s something that feels like artistry in ChatGPT’s responses to prompts.  (See, e.g., this poem by ChatGPT and the debate around whether ChatGPT’s poetry is “art.”)

If ChatGPT sees itself as art rather than science, then we should take it at its word and think of it as we do art and artists.  That is, as do artists, ChatGPT brings a particular perspective to its responses.  As such, ChatGPT’s response is a form of art—and only one of many responses available.  Just like painters and sculptors can interpret their objects of study differently, ChatGPT’s interpretation of data in a particular response is one of many.  Thinking of this another way, we might view ChatGPT’s responses to prompts as opinions, subject to issues of perspective, interpretation, accuracy, bias, and incompleteness.

            ChatGPT Speaks Like It Wants to Sell You Something, but Should You Buy It?

Although I asked ChatGPT to describe a relationship between two things, ChatGPT’s response feels more like a sales pitch. It makes grand, authoritative-sounding claims about ChatGPT’s value to the user.  It is confident that it can help lawyers persuade and compel by providing “high-quality content in a wide range of styles and formats.”  ChatGPT reminds us that it has “key advantages,” that it can enhance the lawyer’s persuasive skill, and that it can generate high-quality content that can be tailored to client’s needs.

Why might ChatGPT sound so confident?  Maybe ChatGPT’s confidence comes from the way it generates responses.  ChatGPT generates responses by examining a vast amount of data, looking for the patterns and relationships between words in the sample, and then predicting what response is appropriate for the context.  Perhaps because I told it I was writing a blog post, the texts that ChatGPT accessed for context were blogs, and because many blogs are written in a tone designed to sell something, this caused ChatGPT to adopt the same tone by predicting that I was expecting that tone in the response.

Regardless of the reason, this extra-confident tone of the response should give us a reason to scrutinize ChatGPT’s claims more carefully.  If we read closely, we see that the response doesn’t really explains what “high-quality content” means.  On one hand, commentators point out that ChatGPT cannot tell the difference between true and false information and thus can deliver inaccurate responses.  This aspect of ChatGPT, then, is not “high-quality.”  Moreover, ChatGPT’s ability to sound very confident in its responses can lure readers into believing the responses’ truth.  For lawyers, this inaccurate information expressed in a confident tone is a malpractice minefield.  For example, one would not want to rely at face value on what ChatGPT says about some point of law.  (It’s probably useful to remind those in your office who could use ChatGPT of this important point.)

On the other hand, ChatGPT arguably can offer something of high(er) quality in that it can produce a “wide variety of styles and formats.”  You can prompt ChatGPT to write in a particular style—even your own!  You can request it write content in the style and organization of a brief or a motion, and it will comply.  You can ask it to assist in correcting your grammar.  It’s pretty good at offering examples of different genres, styles, and tones of writing.  This is because it is good at providing an approximation of whatever you’ve asked it to create based upon the patterns it recognizes in the dataset.

But here’s the catch, I think, with using ChatGPT to generate “style and format” content: the user must already understand the style and structure he or she seeks in order to evaluate the quality of ChatGPT’s response.  In other words, if you don’t know already what a case caption for, say, the United States Court of Appeals for the Ninth Circuit looks like, how can you be sure ChatGPT will give you the right format for that caption?  Likewise, if you aren’t sure what a good introduction to an appellate brief looks like, how can you know if ChatGPT has given you a good one in its response?   ChatGPT would be good at giving you examples, but it can’t really tell you which one is “best” in your circumstances.

            ChatGPT Knows Its Rhetorical Limits

Even though ChatGPT is confident in its capabilities, it admits that it has limits.  Specifically, ChatGPT responds that it cannot understand emotion, context, or intent like a human does when crafting responses to persuade. This is a pretty significant admission.  To be limited in these ways is relevant to ChatGPT’s persuasive abilities; understanding emotion, content, and intent are elements of human communication that are central to rhetorical effectiveness.  So, even though ChatGPT sees itself as an “extension” of rhetoric, it is a fairly limited extension.

 ChatGPT reminds us that one of its limitations is that it generates persuasion from finding patterns in large amounts of existing data.  So, that raises the problem of “garbage in,” “garbage out.”  In other words, the quality of ChatGPT’s responses is only as good as the data it can access.  That is, if the dataset has both helpful and unhelpful patterns that inform ChatGPT’s responses, how does one know if what ChatGPT generated is something worth relying on?  The only way to know is to already have the knowledge essential to evaluating the response.

            In the End, ChatGPT is Deferential about Its Writing

ChatGPT says it is the appellate lawyer’s job to ensure what ChatGPT writes is effective for the intended audience.  It talks about itself as a “model” that can help lawyers be persuasive and reminds lawyers that the model should be used in conjunction with lawyers’ expertise and insights.  In other words, ChatGPT does not take the position that it replaces humans in the writing process—particularly where audience analysis and professional expertise is involved.  Here, ChatGPT makes a significant rhetorical move—it reminds you that the technology is only as good as its user and, even after all of its confidence above, disclaims responsibility for the usefulness of its output. Fascinating.

Some Takeaways

ChatGPT notes that it is new enough that “best practices” for using ChatGPT in legal writing are still being developed. I take this as a challenge!  Based upon ChatGPT’s rhetoric (i.e., the way it uses language to talk about itself), I’ll propose some best practices for you:

  • Do not be misled by ChatGPT’s confidence. ChatGPT sounds confident and authoritative in its responses, but users should be skeptical about the legitimacy of that confidence.
  • Rely on your own expertise, not ChatGPT’s. Appellate lawyers (and staff working for them) need to have an existing knowledge base to evaluate ChatGPT’s responses.  In particular, evaluating the appropriateness of the response for an audience is essential.  As with all aspects of outsourcing judgment in legal practice, outsourcing judgment to ChatGPT is dangerous.  At the very least, for appellate lawyers to use ChatGPT effectively, they will need to become familiar with prompt engineering techniques that make ChatGPT more expert in the field and thus arguably improve ChatGPT’s responses.
  • Treat ChatGPT as opinionated, not authoritative. Although ChatGPT is the product of science, ChatGPT should be seen as an artistic process, generating content that is more like opinion than unassailable fact.  Treat ChatGPT as conversation partner, muse, or collaborator than can help you “play” with ideas and text.  (Check out Ian Bogost’s article insightfully concluding that “ChatGPT  . . . doesn’t understand or even compose text. It offers a way to probe text, to play with text, to mold and shape an infinity of prose across a huge variety of domains . . . into structures in which further questions can be asked and, on occasion, answered.)
  • Remember that ChatGPT relies on pattern recognition, a limited mode of persuasion. ChatGPT does not have all the rhetorical capabilities of humans but can recognize patterns in data that might have persuasive impact.  Even if that pattern recognition is persuasive, users must remember to look at persuasion from all aspects of the human experience, not just in the ways that ChatGPT looks at it.
  • Remember that ChatGPT does not guarantee competent writing, you do. At bottom, ChatGPT does not claim it is superior to you in writing ability but rather it remains deferential to your experience and expertise. It disclaims its ability to effectively write for your “local” audience.  No one—not even a computer—knows your clients, your arguments, and your audience better than you do.  Rely on your own judgment about competent writing.

What are your thoughts?

Kirsten Davis teaches at Stetson University College of Law and in the Tampa Bay region of Florida. She is the Co-Director of the Institute for the Advancement of Legal Communication. The Institute’s mission is to study legal communication issues and provide programming and training that improves legal communication skills. Among other things she’s up to right now, she’s currently working on a writing handbook written specifically for trial lawyers. The views she expresses here are solely her own and not intended to be legal advice. You can reach Dr. Davis at [email protected].

March 2, 2023 in Appellate Advocacy, Appellate Practice, Legal Profession, Legal Writing, Rhetoric | Permalink | Comments (1)

Monday, February 27, 2023

ChatGPT & Grammar

This past weekend I was at a conference in Las Vegas. At the conference, my colleague Diana Simon presented on her recent book--The (Not Too Serious) Grammar, Punctuation, and Style Guide to Legal Writing. During the social time after the presentation, someone asked how ChatGPT handles grammar.  While many professors are stressing over student use of ChatGPT, some professors are considering a key question: Can ChatGPT help me grade papers (at least grade grammar)?

I was mostly just eavesdropping while the professors were discussing grammar, but at least one person noted that ChatGPT does a pretty decent job, and it can give you explanations. Turns out that is right. Stephen Horowitz, a professor of Legal English at Georgetown, has a detailed blog post on how he used ChatGPT for an assignment with his LLM students. For the assignment, he had his students run a short essay through ChatGPT with the instruction to "Please fix any language issues in this essay."

While I commend the full post to you, I will share just his conclusion: 

What I really liked about the assignment is that it succeeded in helping my students build grammatical awareness. Also, I think my students greatly appreciated a way to get detailed language feedback. In my class, while I provide language feedback to the extent it connects to the communicative purposes related to legal analysis and writing, it’s not a grammar class and I don’t have the bandwidth to provide detailed language feedback on every aspect of the students’ writing. (A statement I’m assuming many in the legal English/legal writing field likely relate to.) Additionally, I believe there’s a certain amount of value in receiving the feedback in a manner removed from the power dynamic associated with the student-teacher relationship, i.e., not from an authority figure who has the power to decide your academic fate, but from a neutral, non-judgmental chatbot. And I think it also opens up the potential for more focused conversations and questions between student and teacher about language and grammar, as it helps narrow down areas of student concern from the perspective of each student.

February 27, 2023 in Current Affairs, Legal Writing, Web/Tech | Permalink | Comments (4)

Sunday, February 19, 2023

When Your Opponent’s Brief is a Headscratcher

 “I’m glad you have to write the reply brief, not me.” That’s the whole email I received from a prominent appellate advocate who had written an amicus brief supporting my position after he had read opposing counsel’s brief. The difficulty he alluded to was not because the responsive brief was so stellar that I would be hard pressed to formulate winning counterarguments. Instead, it was because the brief was such a head-scratcher. We weren’t just ships passing in the night; we were sailing in different oceans.

When that’s the case, writing a reply brief can be extraordinarily difficult. It is far easier to argue with an opponent who engages you than one that seems to have dropped in from another case altogether. A well-researched and disciplined brief provides a better foil than one that lacks a theme or anything solid to refute.

More typically in a reply brief, one can argue that one set of precedents is more relevant than another, that key cases were misconstrued by your opponent and the court below, or that the issue presented is one of first impression, requiring a new rule. Yet, when the opposing brief states seemingly valid propositions that relate to the case but not to the issue presented, it is tempting to say that the brief fails in every way to address the appellants’ arguments and that those arguments remain valid and should be adopted by the Court. And, there is certainly good reason to make sure the court understands why the arguments made by your opponent lack relevancy.

Yet, underlying the propositions of law proffered by my opponent were assumptions, sometimes unexpressed, that clarify why that brief provides no useful guidance to a court. In my brief, I labeled them fallacies that constituted an act of misdirection. I ran through six separate fallacies that knocked the legs out from under those arguments – at least, to me, they powerfully served that purpose.

For example, my opponent argued that a rule of civil procedure cannot alter substantive law. We know that that is a correct statement of law. Federal law, 28 U.S.C. § 2072(b), denies civil rules from abridging, enlarging, or modifying any substantive right. Having made the valid point, then opposing counsel did little to connect that to the rule at issue. He asked the court to assume that my argument would make the rule substantive. And, my reply demonstrated that following the proper procedure implements the underlying substantive law, rather than changes it.

Similarly, he recited the holding of a case I cited, as though that holding is the sum total of the analysis, because our case did not fit that holding. Yet, my brief suggested that the type of analysis employed in the case supported the analysis appropriate to the issue. While dicta of the type I relied upon does not formulate binding precedent, it was from the U.S. Supreme Court and therefore takes on a heightened character. As the Sixth Circuit put it recently, “Supreme Court dicta is persuasive and cannot be ignored by lower courts for no good reason.” Cunningham v. Shoop, 23 F.4th 636, 659 (6th Cir.), cert. denied, 143 S. Ct. 37 (2022).

It is also tempting to ignore, for good reason, a brief you believe fails to advance your opponent’s case. Prudence, however, requires that you make clear to the court that your version of the case is the one that it should entertain.

February 19, 2023 in Appellate Advocacy, Appellate Practice, Federal Appeals Courts, Legal Writing, State Appeals Courts, United States Supreme Court | Permalink | Comments (2)