Use of AI, Including Large Language Models (LLMs), in Tax Court Brief Writing (And Really Other Legal Analysis) (1/22/25; 4/29/25)

 AI (artificial intelligence) is ubiquitous now; or at least the discussion of AI is ubiquitous. See generally Artificial intelligence. (2025, January 22), Wikipedia, here.  I asked ChatGPT about use of AI by lawyers and received the response linked here. I write today on some instances recently called to my attention of misuse of AI in briefing in Tax Court cases, but I understand that similar misuse has been identified in briefing in other courts.

Use of AI in legal briefing has received considerable attention, from general discussion of the strengths and weaknesses to specific instances where lawyers have been called out when they used AI that failed. E.g., Is AI a Good Tool for Legal Brief Writing? (Spellbook 10/22/24), here (general discussion, but noting in part for today’s blog that “AI tools can sometimes "hallucinate" information and generate fake citations that human lawyers must carefully check.”); What Are the Best AI Tools for Writing Legal Briefs? (Bloomberg Law 6/10/24), here (nothing that AI in large language models (“LLM”) can produce “false information” via what are called “hallucinations;” and that, as a result, “21 federal trial judges have issued standing orders regarding AI, and attorneys are often required to disclose all uses of AI.”) Suffice it to say that my understanding is that AI generated content must be carefully checked and appropriate revisions made before submitting that content in a brief submitted to the court. (This is confirmed by my limited use of AI as discussed at the end of this blog.)

The Tax Court has no formal rule addressing the use of AI. However, a reader recently advised me of two Tax Court Orders by Judge Buch addressing the issue. Thomas v. Commissioner (T.C. Dkt 10795-22 at #36 Order dtd 10/23/24), here; and Westlake Housing, L.P. v. Commissioner (T.C. Dkt. No. 478-24L at # 32 Order dated 1/13/25), here. (I have posted both orders to my Google Docs to permit a permalink that readers can directly access without having to go through the DAWSON docket sheet which does not offer a permalink for direct access to the orders.)

Thomas is a short order (5 pages); Westlake is even shorter (2 pages). I discuss Thomas in some detail. The Court (Judge Buch) sets the issue up in its opening paragraph:

          This case was tried on September 17, 2024, in Atlanta, Georgia. In preparing for trial, the Court noticed that some of the authorities cited in petitioner’s Pretrial Memorandum did not exist, evidencing possible AI hallucinations. To inquire into these authorities, the Court held a hearing to provide petitioner’s counsel an opportunity to clarify the Pretrial Memorandum. During that hearing, petitioner’s counsel explained that someone else had prepared the Pretrial Memorandum, and she did not review the work that was provided to her. Rule 33 instructs that, in signing a pleading, counsel is certifying that he or she has read the pleading, that it is well grounded in fact; and that it is warranted by existing law. Because the Pretrial Memorandum violates this standard, we will deem it to be stricken. We will also take this occasion to address the use of AI as a tool to assist petitioners and practitioners. As discussed below, however, striking the Pretrial Memorandum will not affect the ultimate outcome in this case.

After then summarizing nicely the role of the Pretrial Memorandum (pp. 1 & 2), the Court noted:

Fun Chevron: AI Weighs in on Chevron’s Future (and Golsen) (12/12/23)

Chevron deference and its possible demise is much in the news recently with the Supreme Court’s acceptance of two parallel cases that address the following question: 

Whether the Court should overrule Chevron or, at least clarify that statutory silence concerning controversial powers expressly but narrowly granted elsewhere in the statute does not constitute an ambiguity requiring deference to the agency.

Loper Bright Enterprises v. Raimondo (SEC) (Sup. Ct. Dkt. 22-451), here; and Relentless, Inc. v. Department of Commerce (Sup. Ct. Dkt 22-1219), here.

I decided to ask various AI platforms what they could offer on whether the Supreme Court will overrule Chevron deference. Here are the answers from three AI platforms (alphabetical order by AI platform without only formatting (such as bold face) offered by the AI; Chevron is not formatted) [Note that I use the free-to-me versions of each platform]:

Bard (Google)

Whether the Supreme Court will overrule Chevron deference is uncertain. While there are indications suggesting both possibilities, ultimately the Court's decision will depend on the specific case and the justices' interpretations of the law.

Arguments in favor of overruling Chevron deference:

• Increased judicial activism: Some argue that Chevron deference grants excessive power to federal agencies, diminishing the role of the judiciary in interpreting the law.
• Lack of democratic accountability: Others argue that agencies are not accountable to the same democratic processes as elected officials, making Chevron deference potentially undemocratic.
• Concerns about agency expertise: Some believe that agencies may not always have the necessary expertise to interpret complex laws.

Arguments in favor of retaining Chevron deference:

• Promotes administrative efficiency: Chevron deference allows agencies to implement and enforce laws without lengthy court challenges, promoting efficiency.
• Recognizes agency expertise: Agencies often possess specialized knowledge and experience relevant to the laws they administer.
• Reduces judicial workload: Deference to agency interpretations can reduce the burden on the courts, allowing them to focus on other matters.

Recent developments:

• Supreme Court agrees to hear case challenging Chevron deference: In May 2023, the Supreme Court agreed to hear a case related to the National Marine Fisheries Service's interpretation of a fishing law. The case could have significant implications for Chevron deference.
• Conservative justices express skepticism: Some conservative justices have expressed skepticism towards Chevron deference, suggesting a potential shift in the Court's stance.

Conclusion:

It is too early to predict whether the Supreme Court will overrule Chevron deference. The Court's decision will likely depend on the specific arguments presented in the case and the justices' individual interpretations of the law. However, recent developments suggest that the Court may be more receptive to challenges to Chevron deference than in the past.

Here are some resources that provide further information on this topic:

• Deference and its Discontents: Will the Supreme Court Overrule Chevron? (CRS Report): https://thehill.com/opinion/judiciary/4238063-what-happens-if-the-supreme-court-overturns-chevron/
• Supreme Court to Consider Major Case on Power of Federal Regulatory Agencies (SCOTUSblog): https://www.scotusblog.com/2021/11/chevron-deference-at-stake-in-fight-over-payments-for-hospital-drugs/
• Supreme Court to Consider Overruling Chevron Deference (Baird Holm LLP): https://www.theregreview.org/2022/07/14/pierce-chevron-deference/  [JAT Note: the link is to an article by Richard Pierce, a noted expert in administrative law]

A Federal Tax Procedure Blog Entry Revised to Style of Hemingway (4/22/23)

I asked two different AI platforms—Google’s BARD and ChatGPT-- to revise a past blog entry in the style of Ernest Hemingway. The Blog Entry is Petition for Writ of Certiorari in NonTax Case Raising Issue of Continued Viability of Chevron (Federal Tax Procedure Blog 3/19/23; 4/17/23), here. (you can click to read; I excluded the text in red from the text I requested the tools to revise to Hemingway style).

GOOGLE BARD

Sure, here is the text you provided in the style of Ernest Hemingway:

The Supreme Court will soon consider whether to overturn Chevron deference, a legal doctrine that allows courts to defer to the interpretations of federal agencies when a statute is ambiguous. The case, Loper Bright Enterprises, Inc. v. Raimondo, involves a dispute over whether the National Marine Fisheries Service (NMFS) has the authority to require domestic vessels to pay the salaries of the monitors they must carry to ensure compliance with regulations.

The petitioners argue that the statute is unambiguous and does not grant NMFS this authority. They also argue that Chevron deference is an unconstitutional delegation of legislative power to the executive branch. The government, on the other hand, argues that the statute is ambiguous and that Chevron deference is a well-established and important legal doctrine.

The outcome of this case could have a significant impact on the balance of power between the executive and legislative branches. If the Court overturns Chevron deference, it will be a major victory for those who believe that the executive branch has too much power. However, if the Court upholds Chevron deference, it will be a victory for those who believe that the executive branch needs to be able to act quickly and effectively in order to carry out its responsibilities.

Here is a more concise version of the text you provided in the style of Ernest Hemingway: