AI Concepts
AI Hallucination in Legal
Definition
An AI hallucination occurs when a language model generates text that appears authoritative but is factually incorrect, such as fabricating case citations, inventing statutes, or misrepresenting holdings. In legal practice, hallucinations carry professional responsibility implications because lawyers have a duty to verify the accuracy of every authority they cite.
Large language models generate text by predicting the most probable next token in a sequence. They do not retrieve information from a verified database; they produce output that is statistically plausible given their training data. This means a model can generate a perfectly formatted Bluebook citation to a case that does not exist, or accurately cite a real case but misstate its holding.
The legal profession has seen high-profile sanctions against attorneys who submitted AI-generated briefs containing fabricated citations. Courts have responded by requiring disclosure of AI use and imposing heightened verification obligations. The risk is especially acute in legal work because the consequences of citing non-existent authority range from embarrassment to sanctions, malpractice claims, and harm to clients.
Mitigating hallucinations requires architectural solutions, not just prompting techniques. Retrieval-augmented generation grounds the model's output in verified legal databases, and citation verification systems check cited cases against authoritative sources and flag references that cannot be confirmed. Neither approach alone is sufficient; the most reliable systems combine both, and neither replaces the lawyer's own review of the cited authority.
How Irys approaches this
Irys addresses hallucination risk through retrieval-augmented generation backed by verified legal databases and an independent verification layer that checks identified case references and surfaces potential citation issues for review.
Related terms
AI Concepts
Retrieval-Augmented Generation (RAG)
Retrieval-augmented generation is an AI architecture that supplements a language model's response by first retrieving relevant documents from an external knowledge base and then using those documents as context for generating an answer. In legal applications, RAG grounds AI output in actual case law, statutes, and firm documents rather than relying solely on the model's training data.
Research
Citation Verification
Citation verification is the process of independently confirming that the legal citations in a document hold up: that the cited authorities exist, that quoted language matches the source, and that the authorities have not been overruled or negatively treated. In AI-assisted legal work it is the step that catches hallucinated or inaccurate references, and it supports the reviewing attorney's own verification duty rather than replacing it.
Research
AI Legal Citations
AI legal citations are case references, statutory citations, and other legal authority references generated by AI systems in the course of legal research or drafting. The accuracy and verifiability of AI-generated citations is a central concern in legal AI because language models can produce citations that appear well-formed but reference non-existent authorities.
Research
Good Law Check
A good law check is the process of verifying whether a cited legal authority remains valid and has not been overruled, reversed, superseded by statute, or otherwise undermined by subsequent legal developments. AI-powered good law checks automate the citator function traditionally performed by Shepard's Citations (Lexis) or KeyCite (Westlaw).
Continue exploring
See AI Hallucination in Legal in action
Irys One brings research, drafting, and document intelligence together in one platform. Try it free for 7 days.