RESEARCHMonitorWATCHLIST
The Detectability Gap: Hidden Heterogeneity in Hallucination Detection Across Language Models
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
arXiv research shows sampling-based hallucination detection misses high-agreement errors ('Ghost' hallucinations) across four LLMs.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 30 September 2026
- Collected by OneBench
- 1 Oct 2026, 03:01 UK
Stored source excerpt
arXiv:2609.35860v1 Announce Type: new Abstract: Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors are…
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.