RESEARCHMonitorWATCHLIST
When Citations Mislead? A Claim-Level Benchmark for Legal Hallucination Detection
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers introduced PARCEL, a legal hallucination benchmark testing if LLM citation claims are backed by NY court authorities.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 9 October 2026
- Collected by OneBench
- 10 Oct 2026, 03:01 UK
Stored source excerpt
arXiv:2610.10971v1 Announce Type: new Abstract: Large language models are increasingly used in legal research and drafting, but they can still produce claims that sound convincing…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.