Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
Journal of Legal Analysis 16(1), 64–93
What it adds
Separates externally checkable answers from contradiction-based hallucination estimates.
Read with this limitation
Contradiction-based estimates are lower bounds; federal-case sampling and historical models do not represent all legal practice.
- Jurisdiction tags
- United States
- Language
- English
Follow the source
Selected statements located in the linked primary sources. These results have not been independently reproduced here.
For sampled verifiable case questions, reported hallucination rates range from 58% for GPT-4 to 88% for Llama 2.
1 IntroductionSampling draws 5,000 cases at each of three federal-court levels.
4.1 Data
Connected research
Same research topic · no citation implied
Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools
Same research topic · no citation implied
Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset
Entry status, source edition & rights
- Index entry
- Source-linked summary, prepared with agent assistance. Independent scholarly review is pending.
- Archive admission
- This bibliographic entry does not confer admission to the versioned archive.
- Edition inspected
- 2401.01301v2
- Reading coverage
- Exact arXiv v2 main methods/results, Figures 1–2, sections 2–6 and artifact description; 80-page document including appendices not exhaustively audited.
- Rights
- External references only. Papers and research artifacts remain with their original hosts; their own terms apply.
- Entry updated
- 2026-10-15
Source-linked summary · independent assessment pending.