# AI Hallucinations in Legal Filings: How to Stop Them

> AI-drafted briefs cite cases that do not exist, and courts are sanctioning for it. Why it happens, what the rules require, and how to catch a fake case.

[Home](https://rankshieldlegal.com/) / [Solutions](https://rankshieldlegal.com/solutions/) / AI Hallucinations in Filings Citation integrity
# A hallucinated case is a Rule 11 problem, not a typo.
**Generative AI invents citations that look perfectly real** — correct reporter format, plausible parties, a persuasive holding — for cases that do not exist. Courts have moved from surprise to sanctions, and the fix is structural: resolve every cited authority against live case-law before the filing is signed.
[Try the citation checker](https://rankshieldlegal.com/ai-legal-citation-checker/) [Request early access](https://rankshieldlegal.com/contact/)

The failure mode is specific and repeatable. A lawyer asks an AI tool to draft an argument or find supporting authority, the tool returns citations formatted flawlessly, and because the format is right the citations survive a human skim. Correct Bluebook form is exactly what a language model is good at reproducing — whether or not the opinion behind it was ever written. That is why the model itself cannot be the safeguard. A [citation check against live case-law](https://rankshieldlegal.com/ai-legal-citation-checker/), run before signature, is what actually stands between a draft and a sanctionable filing. This page explains why the fabrication happens, what the rules now demand, and the concrete steps that catch a fake case before it reaches a judge.

## Why does AI fabricate citations that look real?
A language model generates text that is statistically plausible, not text that has been checked against a record of what exists. It predicts the next token from patterns in its training data, and Bluebook citation format is one of the most regular patterns in all of legal writing. So the model reproduces it almost perfectly: a real-looking reporter and volume, a clean pincite, a confident parenthetical, parties whose names sound exactly like litigants in that area of law. Every surface signal a lawyer uses to judge a citation at a glance is a signal the model is good at faking.
What the model cannot do on its own is guarantee that the opinion behind the citation was ever handed down. It has no live connection to a case-law database at the moment it writes, and it is not consulting one — it is composing something that fits the shape of an answer. When the true authority is thin, the model does not stop; it fills the gap with a citation that looks like the ones it has seen. The result is a fabrication that is indistinguishable from a real cite until someone actually pulls the case. Perfect formatting must therefore never be treated as evidence that a case is real. It is the very trait that makes fabricated citations dangerous.

## What makes a hallucinated citation so hard to catch by eye?
**Formatting is not verification.** The only thing that confirms a case exists is matching its exact reporter citation against live case-law and finding the real opinion. Everything else is a guess dressed as a fact. A misspelled name or a garbled reporter number triggers suspicion. A perfectly formed citation does the opposite — it reassures. Fabricated authorities pass review precisely because nothing about them looks wrong. The parties are plausible, the court is one that would plausibly hear the matter, the quoted holding says what the brief needs it to say, and the citation slots cleanly into a string cite next to authorities that are genuine. Reviewers reading under deadline are pattern-matching for errors, and a hallucination presents none of the usual ones.
The danger compounds inside a long brief. A single fabricated case sits among a dozen real ones, and the real ones lend it credibility by association. Associates assume a partner checked it; partners assume the associate or the research tool did. Nobody pulls all forty citations, because pulling all forty by hand is exactly the tedious work the AI tool was supposed to save. The gap between "looks verified" and "is verified" is where these filings go wrong, and no amount of careful reading closes it — only actually resolving each citation against the published record does.

## How big is the problem, and is it getting worse?
Two independent lines of evidence point the same direction. The first is measurement of the tools themselves. A Stanford RegLab study, published in the Journal of Empirical Legal Studies, tested leading legal-AI research products and found they still hallucinate on a meaningful share of queries — roughly 17% for one major provider's tool and about a third for another — with general-purpose chatbots far higher still. These are the purpose-built, retrieval-backed legal tools, not raw consumer chatbots, and they still get authorities wrong often enough that the model can never be the last line of defense.
The second line is what reaches courts. Public trackers that catalog AI-hallucination filings now list well over a thousand matters worldwide involving fabricated or misused authorities, and the count grows steadily as more are found and reported. Treat that number as directional rather than precise — new entries are added constantly, which is itself the signal. The pattern is not a handful of embarrassing outliers; it is a systemic failure mode that follows the adoption curve of the tools.
~17–33% hallucination rate a **Stanford RegLab study** found across leading legal-AI research tools
1,000+ filings worldwide catalogued by public trackers as involving AI-fabricated or misused authorities (directional, growing)
$5,000 landmark sanction in **Mata v. Avianca**; some later matters have reached six figures

## What do the federal rules require right now?
**The through-line is consistent.** A filer is expected to be able to show that cited authorities exist and were checked. The safe posture is not "we used a careful model" — it is "we resolved every citation against live case-law and can prove it." One is an assurance; the other is evidence a court can check. The professional expectation has hardened from norm into written obligation, and it now sits at three levels. At the base is Federal Rule of Civil Procedure 11, which is not new and did not need amending to apply here: by signing a filing, an attorney certifies that the legal contentions are warranted by existing law and that a reasonable inquiry preceded the filing. A citation to a case that does not exist fails that certification on its face, whether or not the lawyer knew the case was fake — Rule 11 asks about reasonable inquiry, not intent.
On top of that, individual judges have issued standing orders addressing AI directly. As one concrete example, Judge Nina Wang of the District of Colorado issued a standing order, effective December 1, 2025, requiring that any AI-assisted authorities in filings be certified as non-fictitious and confirmed by a human before submission. Orders like it convert a general duty of inquiry into a specific, per-filing certification you either can or cannot make. And at the national level, a proposed amendment to Rule 11 addressing AI-generated authorities is before the Advisory Committee. It is a proposal, not adopted law, and should be treated as one — but the direction of travel is unmistakable.
Layer What it requires Status
FRCP Rule 11 Reasonable inquiry; legal contentions warranted by existing law; signature certifies both In force nationwide
Judge Wang standing order (D. Colo.) Certify AI-assisted authorities are non-fictitious and human-reviewed Effective December 1, 2025
Proposed FRCP Rule 11 amendment Extend an AI-authorities duty more broadly across federal practice Proposal before the Advisory Committee — not adopted

## Does using AI to draft a brief expose me to sanctions?
This is the question that most needs a straight answer, because the headlines blur it. The tools are permitted. What courts have generally sanctioned is the failure to verify — signing a filing with fabricated or unchecked authorities — not the fact that AI was used somewhere in the drafting. The distinction matters, because it tells you what to fix. You do not have to abandon AI to be safe; you have to close the gap between generating a citation and confirming it, and to be able to show that you did.

- Myth Using AI to draft a brief is what gets lawyers sanctioned. Truth Courts have generally sanctioned the **failure to verify** — filing fabricated or unchecked citations — not the use of AI itself. The duty is to confirm authorities before you sign.
- Myth A careful, well-reviewed AI model won't hallucinate citations. Truth Even leading legal-AI tools hallucinate on a meaningful share of queries, per the Stanford RegLab study. The model cannot be the safeguard; an existence check against live case-law is.
- Myth If the Bluebook formatting is perfect, the case is real. Truth Perfect formatting is exactly what a language model reproduces well. It says nothing about whether the opinion exists — only a match against published case-law does.
- Myth Any tool can promise hallucination-free filings. Truth No honest tool can. What verification does is **certify which citations are real** — and an existence check is only ever as complete as the case-law corpus it searches.

## What did the Stanford RegLab study actually find?
It is worth being precise about the evidence, because it is often misquoted in both directions. A Stanford RegLab study, published in the Journal of Empirical Legal Studies, evaluated the retrieval-augmented legal-research tools sold specifically to lawyers — the products marketed as grounded in real case-law, not consumer chatbots. Even those tools produced hallucinated or misgrounded answers on a substantial fraction of queries, on the order of roughly one in six for one leading tool and closer to a third for another. General-purpose language models tested elsewhere fared considerably worse.
The point of citing the study is not to disparage any product. It is to establish a design principle: if the best-resourced, retrieval-backed legal tools still err at those rates, then trusting any model's output as self-verifying is unsound. The correct architecture puts a deterministic existence-and-quotation check between the model and the filing — one that either finds the real opinion or does not, with no probability involved. That is the difference between a tool that is usually right and a control you can rely on.

## How do you catch a fabricated case before you file?
The verification has to be mechanical, not a matter of judgment, because judgment is what fabricated citations defeat. Four checks, run against the published record rather than against the model that produced the draft, catch the failure modes that matter.

- **Resolve existence** Match every citation against live case-law by its exact reporter citation — not the case name, which a model can invent convincingly. Either the real opinion comes back, or the citation is flagged as unverifiable. There is no middle answer.
- **Check the quotation** Compare each quoted passage against the text of the published opinion. This catches the subtler failure: a real case cited for a holding it never stated, or a quotation the model composed to fit the argument.
- **Confirm good law** Overlay good-law standing from your firm's citator, so an overruled, vacated, or superseded authority is flagged even when the case itself is real and correctly quoted.
- **Certify, don't just flag** Produce a signed, sealed certificate of exactly what was checked and what it found, so the verification becomes evidence you can hand a court rather than an assertion you have to be believed on.

## What does a verification workflow need beyond an existence match?
An existence check is necessary but not sufficient. A citation can be real and still wrong for the brief in ways that draw a rebuke — or a sanction — as surely as a fabrication does. A durable workflow layers several checks and, critically, records the result of each.

- **Exact-citation matching, not name matching** — resolve by reporter citation, because a plausible case *name* is the easiest thing for a model to invent and the easiest thing for a reviewer to accept.
- **Quotation fidelity** — verify that quoted language actually appears in the opinion, and appears in the sense the brief uses it, catching misquotes and out-of-context pulls.
- **Good-law standing** — draw currency from your firm's citator so overruled or questioned authorities are surfaced, not just non-existent ones.
- **Coverage honesty** — record which corpus was searched, because an existence check is only as complete as the case-law it can see; an unindexed jurisdiction is a gap, not a clean bill.
- **A durable record** — capture what was checked, when, against what source, and with what result, so the work survives as evidence rather than living only in someone's memory of having looked.

## Why does certification produce evidence a court can check?
A dashboard that turns green tells you a check ran. It does not let a judge, a client, or an opposing party confirm that it ran, or see what it found — they have to take your word. Certification is built to remove that trust requirement. When each citation is resolved, the outcome is recorded in a certificate that states three things: that the authority exists as an exact match against live case-law, that the quotations were checked against the opinion, and that good-law standing was confirmed from the firm's citator.
That certificate is then signed with post-quantum digital signatures — ML-DSA and SLH-DSA — and sealed to an RFC 6962 transparency log, the same append-only, publicly verifiable log structure used for certificate transparency on the web. The signature proves the certificate came from the firm and was not altered; the log seal proves it existed at the stated time and has not been backdated or quietly edited since. Anyone can verify both without trusting the firm and without access to its internal systems. That is what turns "we checked" from a claim into [verifiable evidence](https://rankshieldlegal.com/why-verifiable/) — and it is the whole premise of [citation certification](https://rankshieldlegal.com/citation-certification/).

## What should a small or midsize firm do this week?
The firms most exposed here are the ten- and thirty-lawyer practices that cannot staff a dedicated citation-verification workflow but carry the exact same Rule 11 duties as a firm ten times their size. The mismatch is the risk, and the answer is not "hire a research team." It is to put a switch-on checkpoint in front of the signature. A few concrete moves, in order of return:

- **Write a one-line filing rule** — no brief goes out until every citation has been resolved against live case-law by its reporter citation. Make it a step in the signature workflow, not an aspiration in a handbook.
- **Verify by citation, never by name** — train everyone that a plausible case name is not evidence of anything, and that the reporter citation is what gets checked.
- **Keep the evidence** — retain a record of the check for every filing, so that if a question is ever raised you can show the work rather than reconstruct it.
- **Cover quotations and good law too** — extend the check beyond existence to what the case says and whether it still stands.
- **Fit it into the broader risk map** — citation integrity is one control among several; see [law firm cybersecurity in the AI era](https://rankshieldlegal.com/law-firm-cybersecurity/) for how it sits alongside privilege and long-lived confidentiality risks.

## How does RankShield Legal fit into this?
RankShield Legal's premise is simple: in a profession built on evidence, your AI controls should produce evidence too. The [AI legal citation checker](https://rankshieldlegal.com/ai-legal-citation-checker/) resolves every cited authority against live case-law by exact citation, checks quotations against the opinion, and overlays good-law standing from your firm's citator. What it does not do is promise "hallucination-free" filings — no honest tool can, and any that claims to is overselling. What it does is certify which citations are real and record precisely what was and was not checked, so the boundaries of the assurance are as visible as the assurance itself.
The output is the point. Each verification produces a certificate signed with post-quantum signatures and sealed to a public transparency log, so a court, client, or insurer can confirm the work independently. That is a control designed for the duty it serves — reasonable inquiry you can demonstrate, not merely assert. See [how it works](https://rankshieldlegal.com/how-it-works/) for the full flow from citation to sealed certificate. This page is informational and is not legal advice; your obligations under Rule 11 and any applicable standing order are yours to meet, and a verification tool is there to help you meet and evidence them.

Early access · Law firms
### Prove it, don't promise it
Certify every citation, attest privilege isolation, and seal each result to a log a court or client can verify. Enterprise-grade protection, firm-sized.
[Request early access →](https://rankshieldlegal.com/contact/) [hello@seoeliteagency.com](mailto:hello@seoeliteagency.com)

Ask anything
## AI Hallucinations in Filings, answered
The questions law firms ask about ai hallucinations in filings, answered directly. **No forms, no sales pitch.**

JAMIE KLONCZ · SEO AGENCY NAPLES ************** ONLINE
Pick a question on the left, or search above. You will get the direct answer, the way an answer engine would give it.

← PREV NEXT → [REQUEST ACCESS →](https://rankshieldlegal.com/contact/)

- **How common are AI-hallucinated citations in real filings?** Common enough that researchers maintain public databases of them, now cataloging well over a thousand filings worldwide involving AI-fabricated or misused authorities, with sanctions ranging from warnings to substantial monetary penalties. The landmark example, Mata v. Avianca, drew a $5,000 sanction; some later matters have reached six figures. Treat the tracker number as directional evidence of a systemic pattern rather than a precise count — new cases are added regularly, which is itself the point. Separately, a Stanford RegLab study found that even purpose-built legal-AI tools hallucinate on a meaningful share of queries, so the underlying failure rate is not a rounding error.
- **Does using AI to draft a brief mean I will get sanctioned?** No. Courts have generally sanctioned the failure to verify, not the use of AI itself. The tools are permitted; the duty is to confirm that cited authorities are real, accurately quoted, and good law before you sign. Federal Rule of Civil Procedure 11 asks whether you made a reasonable inquiry, not whether you used software to draft. So the fix is not to stop using AI — it is to place a citation check between the draft and the signature, and to keep evidence that the check ran. Certification is how you meet that duty and preserve the proof, rather than a reason to abandon a useful tool.
- **Can I just tell my associates to double-check every AI citation?** A manual policy helps but fails under deadline pressure, and it leaves you with no evidence you followed it. Fabricated citations survive precisely because they look correct on a skim — perfect formatting, plausible parties, a persuasive holding. An automated existence check against live case-law catches what a human eye misses, because it matches the exact reporter citation rather than trusting the appearance of one. And a certificate gives you a durable record that the check ran, against what corpus, with what result — which a reminder in a handbook does not. Use the policy to set the expectation and the tooling to actually meet it.
- **What exactly did the Stanford RegLab study find?** A Stanford RegLab study, published in the Journal of Empirical Legal Studies, tested the retrieval-backed legal-research tools sold to lawyers and found they still hallucinate on a meaningful share of queries — on the order of roughly 17% for one leading tool and about a third for another, with general-purpose chatbots far higher. These are the products marketed as grounded in real case-law, not consumer chatbots. The takeaway is not that any one product is bad; it is that no model's output should be trusted as self-verifying. A deterministic existence-and-quotation check between the model and the filing is what makes the difference between a tool that is usually right and a control you can rely on.
- **Why check by reporter citation instead of the case name?** Because the case name is the easiest thing for a language model to invent convincingly. A plausible-sounding name — the right kind of parties, in the right kind of dispute — is exactly what the model is good at generating, and exactly what a reviewer is inclined to accept. The reporter citation, by contrast, has to resolve to a specific published opinion or it does not resolve at all. Matching by exact citation gives a binary answer: the real opinion comes back, or the citation is flagged as unverifiable. Matching by name invites false confidence, because a name can look right while pointing at nothing.
- **What does certification give me that a research tool's checkmark does not?** A checkmark tells you a check ran; certification lets others confirm it. Each verified citation produces a certificate stating that the authority exists as an exact match against live case-law, that quotations were checked against the opinion, and that good-law standing was confirmed from your firm's citator. The certificate is signed with post-quantum signatures (ML-DSA and SLH-DSA) and sealed to an RFC 6962 transparency log, so its contents and timestamp can be verified by anyone without trusting your systems. That converts "we checked" from an internal assertion into evidence a court, client, or insurer can independently check — which is what the duty of reasonable inquiry ultimately calls for.
- **Can any tool guarantee hallucination-free filings?** No, and you should be wary of one that claims to. What verification can honestly do is certify which citations are real, which quotations match, and which authorities are still good law — and record which corpus it searched, because an existence check is only ever as complete as the case-law it can see. A citation in an unindexed jurisdiction is a coverage gap to disclose, not a clean result to assume. The honest framing is not "we eliminated hallucinations" but "we resolved every citation we could against live case-law, certified the result, and made the limits of that check visible." That posture is both more truthful and more defensible than a guarantee no tool can keep.

Keep exploring
## Related work
[Platform AI Citation Checker The fastest way to catch a fabricated case: resolve every citation against live case-law, then certify the filing. Explore →](https://rankshieldlegal.com/ai-legal-citation-checker/)[Platform Citation Certification Existence, quotation, and good-law standing for every authority — issued as a verifiable certificate, not a flag. Explore →](https://rankshieldlegal.com/citation-certification/)[Solutions Law Firm Cybersecurity The AI-era risk map for small and midsize firms — and the verifiable controls that answer each risk. Explore →](https://rankshieldlegal.com/law-firm-cybersecurity/)