Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
- Source type
- Academic Paper
- Published
- 6 Oct 2026
- Added by
- IKECHUKWUKoinovera team
- Added
- 6 Oct 2026
Contributor evidence
What this source establishes
Tests on verifiable US legal questions found frequent incorrect and invented legal claims. Shows citation-like factual failures in a high-stakes domain.
Limitations
Legal hallucinations include more than fabricated citations; task mix affects rates.
AI evidence analysis
Koinovera can compare extracted source evidence against this claim. The result is advisory and may be wrong.
Sign in to analyse evidenceHow readers rated this source
These rate the source itself, wherever it is cited. The reasoning built on it is rated on each case.
No one has rated this source yet.
Sign in to rate this source