Fabricated vs. Misgrounded: The Two Ways Legal AI Gets Citations Wrong

Yes, AI hallucinates case law, and it does so in two distinct ways. A fabricated citation points to a case that does not exist. A misgrounded citation points to a real case but attaches a holding, quote, or proposition the opinion never supports. Each failure mode is caught by a different verification check, which is why one review method alone is not enough.

Yes, AI invents case law, in two distinct ways

AI does invent case law, and treating it as a single problem is the first mistake. There are two separate failure modes with different causes and different fixes. Fabrication produces a citation with no real case behind it. Misgrounding produces a citation to a genuine case that the AI has quietly misread. Stanford RegLab found that leading legal AI research tools, including retrieval-grounded ones, hallucinate on "1 in 6 or more" queries [1]. Damien Charlotin's public database now catalogs more than 1,300 court proceedings flagging suspected AI hallucinations, updated daily [2]. Both numbers describe a moving target, not a solved one. Because the two modes look identical on the page, a reviewer who only scans for names that "look wrong" will catch fabrications while waving misgrounded citations straight through to a signed filing.

Fabricated citations: the case does not exist

A fabricated citation is the failure most people picture: the AI invents a case that was never decided. The party names are made up, the reporter volume and page are made up, and sometimes the court and year are made up too. Nothing resolves to a real opinion because there is no opinion. These are the citations behind the most widely reported sanctions, and they are also, paradoxically, the easier mode to catch. A fabricated case fails the simplest possible test: existence. When you try to pull the opinion from a reliable reporter or database, there is nothing to retrieve. Fabrication tends to spike when a model is asked about a narrow or obscure area of law where its training data is thin, so it fills the gap with a plausible-sounding invention. The reviewer's job here is mechanical but essential: confirm that every cited authority actually exists before anyone relies on it.

Misgrounded citations: a real case, the wrong proposition

A misgrounded citation is more dangerous because it survives a surface check. The case is real. The citation format is correct. You can pull the opinion and hold it in your hand. The problem is what the AI claims the case says. It attributes a holding the court never reached, inserts a quotation that appears nowhere in the text, or cites the case for a proposition it does not support, sometimes for the exact opposite of what it holds. Because the citation resolves cleanly, existence checks pass and the error slides through. This is the mode that grounding was supposed to solve and only partially does. Catching a misgrounded citation requires reading the opinion and matching each quotation and proposition against what the case actually stands for, which is slower, harder, and easier to skip under deadline.

Why "grounded" and RAG tools still miss one mode

Retrieval-augmented generation was meant to end hallucination by tethering the model to real documents. It reduces fabrication meaningfully, because the model is pulling from actual retrieved cases rather than inventing them. But grounding does not eliminate misgrounding. Stanford RegLab tested purpose-built, retrieval-grounded legal research tools and still measured hallucination rates above 17% for one product and above 34% for another [1]. The reason is structural: retrieval fetches a real case, but the model can still summarize it wrong, quote it inaccurately, or apply it to a proposition it does not support. The document is real; the interpretation is not. This is the misgrounded failure mode, and it is precisely the one that a "we use RAG" assurance does not close. Grounding narrows the gap between the model and the record. It does not guarantee the model reads the record correctly.

Matching the right check to each failure

Each failure mode maps to a specific verification method, and using the wrong one leaves a gap. Existence resolution catches fabrication: attempt to retrieve every cited authority, and anything that does not resolve is invented. Quotation and proposition matching catches misgrounding: pull the real opinion and confirm each quote appears in it and each proposition is actually supported. A citator catches a third, adjacent problem, bad law: a citation that is real and accurately described but has been overruled, vacated, or superseded. Bad law is not a hallucination in the strict sense, because the AI read the case correctly, but it fails a filing just as effectively. Running only one of these checks leaves the others open. A complete review confirms three things about every authority: that it exists, that it is quoted and applied accurately, and that it remains good law.

Frequently asked questions

Does AI make up case law?

Yes. AI can and does invent case law, producing citations with fabricated party names, reporter volumes, and page numbers that point to no real opinion. Stanford RegLab found that leading legal AI research tools, including retrieval-grounded ones, hallucinate on "1 in 6 or more" queries [1], and Damien Charlotin's database catalogs more than 1,300 court proceedings flagging suspected AI hallucinations [2]. Fabrication is the most-reported failure because it produces the dramatic sanctions, but it is also the more detectable of the two modes, since an invented case fails a simple existence check the moment someone tries to retrieve it.

What is a misgrounded citation?

A misgrounded citation points to a real, existing case but attributes to it something the opinion does not actually contain: a holding the court never reached, a quotation found nowhere in the text, or a proposition it does not support, occasionally the opposite of what it holds. It is more dangerous than a fabrication because it passes surface review. The citation resolves to a genuine opinion, so anyone checking only whether cases exist will approve it. Catching it requires reading the opinion itself and matching every quote and proposition against the actual text.

Can grounded or RAG legal AI still hallucinate?

Yes. Retrieval-augmented generation reduces fabrication by tethering the model to real retrieved documents, but it does not eliminate misgrounding. Stanford RegLab measured hallucination rates above 17% and above 34% for two purpose-built, retrieval-grounded legal research tools [1]. Grounding fetches a real case, but the model can still summarize it incorrectly, quote it inaccurately, or apply it to an unsupported proposition. The document is genuine; the interpretation is not. A "we use RAG" assurance narrows the gap between model and record but does not guarantee the record is read correctly.

RankShield Legal is a verifiable AI and quantum security platform for law firms: it certifies that cited authorities exist, are quoted accurately, and are good law before a filing is signed. This article is general information, not legal advice; consult a licensed attorney about your situation.

References

[1] Stanford RegLab (Magesh, Surani, Dahl, Suzgun, Manning, Ho). Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools. Journal of Empirical Legal Studies, 2025 (preprint May 2024). https://hai.stanford.edu/news/ai-trial-legal-models-hallucinate-1-out-6-or-more-benchmarking-queries

[2] Charlotin, D. AI Hallucination Cases database. 2026. https://www.damiencharlotin.com/hallucinations/