AI Hallucination Case Stemming from Use of a Paralegal's AI-Based Research

I blogged yesterday about AI hallucinations in court filings by prominent law firms, as well as a nonexistent source cited in an expert’s declaration (the expert works for leading AI company Anthropic, though at this point it’s not yet clear whether the error stemmed from an AI hallucination or from something else). But I thought I’d blog a bit more in the coming days about AI hallucinations in court filings, just to show how pervasive the problem is: I’m seeing court decisions about this every few days. And those decisions are likely just the tip of the iceberg, since many hallucinations won’t be noted in court decisions, and the great majority of court decisions are state trial court decisions that don’t show up on Westlaw.

Here’s the first case that showed up in my daily WestClip query related to the subject, an opinion yesterday by Judge Rachel Kovner (E.D.N.Y.) in Ramirez v. Humala:

Plaintiff Ramirez’s response letter, … signed by [her lawyer,] Ms. Stillman, cites eight cases. Of the eight, the Court was unable to locate four: (1) London v. Polish Slavic Fed. Credit Union, No. 19-CV-6645, 2020 WL 1275619 (E.D.N.Y. Mar. 17, 2020); (2) Rosario v. 2022 E. Tremont Hous. Dev. Fund Corp., No. 21-CV-9010, 2023 WL 1993700 (S.D.N.Y. Feb. 14, 2023); (3) Paniagua v. El Gallo No. 3 Corp., No. 22-CV-7073, 2024 WL 1046856 (S.D.N.Y. Mar. 11, 2024); and (4) Luna v. Gon Way Constr., Inc., No. 20-CV-893, 2022 WL 826856 (S.D.N.Y. Mar. 18, 2022). The Court ordered Ms. Stillman to either provide copies of the four cases or show cause why she should not be sanctioned for citing nonexistent cases pursuant to Federal Rule of Civil Procedure 11(b) and the inherent power of the Court.

Stillman explained that this originated in the work of her paralegal:

Ms. Ruiz[, Ms. Stillman's paralegal,] explains that she took the initiative to assist with the legal research for the reply and generated the citations at issue “using secondary tools, including public search resources and AI-based research assistants.”). Ms. Ruiz did not check that the citations she had generated corresponded to real cases before passing them to Ms. Stillman. Ms. Stillman, in turn, relied on Ms. Ruiz, “a diligent and trusted member” of the team, and “did not independently verify each citation prior to filing.”

Federal Rule of Civil Procedure 11(b)(2) provides:

By presenting to the court a pleading, written motion, or other paper—whether by signing, filing, submitting, or later advocating it—an attorney … certifies that to the best of the person’s knowledge, information, and belief, formed after an inquiry reasonable under the circumstances: … the claims, defenses, and other legal contentions are warranted by existing law or by a nonfrivolous argument for extending, modifying, or reversing existing law or for establishing new law.

“A fake opinion is not ‘existing law’ and citation to a fake opinion does not provide a non-frivolous ground for extending, modifying, or reversing existing law, or for establishing new law.” Accordingly, the Second Circuit, as well as district courts across the country, have found the submission of nonexistent case citations in filings to the court to constitute sanctionable conduct under Rule 11(b)(2). See, e.g., Park v. Kim, 91 F.4th 610, 613–16 (2d Cir. 2024); Mata v. Avianca, Inc., 678 F. Supp. 3d 443, 461 (S.D.N.Y. 2023); Gauthier v. Goodyear Tire & Rubber Co., No. 23-CV-281, 2024 WL 4882651, at *2–3 (E.D. Tex. Nov. 25, 2024); Wadsworth v. Walmart Inc., 348 F.R.D. 489, 495–96 (D. Wyo. 2025); Dehghani v. Castro, No. 25-CV-52 (MIS) (DLM), 2025 WL 988009, at *4 (D.N.M. Apr. 2, 2025); Nguyen v. Savage Enters., No. 24-CV-815 (BSM), 2025 WL 679024, at *1 (E.D. Ark. Mar. 3, 2025); Bevins v. Colgate-Palmolive Co., No. 25-CV-576, 2025 WL 1085695, at *7 (E.D. Pa. Apr. 10, 2025); Benjamin v. Costco Wholesale Corp., No. 24-CV-7399 (LGD), 2025 WL 1195925, at *6–8 (E.D.N.Y. Apr. 24, 2025).

Ms. Stillman’s conduct violated Rule 11. “Rule 11 explicitly and unambiguously imposes an affirmative duty on each attorney to conduct a reasonable inquiry into the viability of a pleading before it is signed.” A reasonable inquiry means, at minimum, that attorneys must “read, and thereby confirm the existence and validity of, the legal authorities on which they rely.” … “[N]o inquiry cannot be deemed objectively reasonable even if the reliance is placed in an experienced attorney.” … Ms. Stillman failed to conduct this minimal inquiry.

Moreover, Ms. Stillman acted with subjective bad faith, as required for the imposition of sua sponte sanctions under Rule 11. Ms. Stillman’s failure to make any inquiry at all into the veracity of the cases provided by her paralegal was so “completely without merit” that subjective bad faith may be inferred. See, e.g., Mata, 678 F. Supp. 3d at 464 (finding subjective bad faith where attorney signed a filing despite “not reading a single case cited … and taking no other steps on his own to check whether any aspect of the assertions of law were warranted by existing law”); Benjamin, 2025 WL 1195925, at *7–8 (similar); cf. United States v. Cohen, 724 F. Supp. 3d 251, 258–59 (S.D.N.Y. 2024) (declining to find subjective bad faith where counsel did not read certain citations but sincerely believed they had been provided by co-counsel who had reviewed them).

In similar cases where sanctions have been imposed on attorneys for the submission of nonexistent, AI-generated cases, monetary sanctions have ranged from $1,000 to $5,000. See, e.g., Mata, 678 F. Supp. 3d at 466 ($5,000 sanction); Gauthier, 2024 WL 4882651, at *3 ($2,000 sanction); Wadsworth, 348 F.R.D. at 498 ($3,000 sanction for the most culpable attorney; $1,000 sanctions each for two less culpable attorneys); Dehghani, 2025 WL 988009, at *5 ($1,500 sanction); Nguyen, 2025 WL 679024, at *1 ($1,000 sanction); Benjamin, 2025 WL 1195925, at *9 ($1,000 sanction). Courts have also imposed nonmonetary sanctions including referral for attorney discipline, see, e.g., Park, 91 F.4th at 616, revocation of an attorney’s pro hac vice admission, see, e.g., Wadsworth, 348 F.R.D. at 498, and mandatory CLE training on the use of AI in the legal field, see, e.g., Gauthier, 2024 WL 4882651, at *3.

A sanction on the low end of the spectrum is warranted here as a result of Ms. Stillman’s prompt admission of error, her and Ms. Ruiz’s apologies to the Court, and Ms. Stillman’s averment that she is “conducting a full internal review of our citation practices and research protocols” to ensure that “any research-based citations in future drafts” will be “pulled directly from Westlaw or PACER and verified by a supervising attorney.” Given these circumstances, a sanction of $1,000 is sufficient but not more than necessary to serve the deterrence purposes of Rule 11.

The court also concluded that the law firm was jointly responsible for the sanction; that’s not practically important here, because the firm appears to be Ms. Stillman’s own, but it may be relevant in other cases. And the court also noted that, “[c]onsistent with common practice, Ms. Stillman shall also inform her client … of these developments by serving a copy of this order on her client.”

The post AI Hallucination Case Stemming from Use of a Paralegal’s AI-Based Research appeared first on Reason.com.