Audit Tests Whether Hallucination Detector Rankings Hold on Small Quantized On-Device LLMs
A new arXiv paper audits hallucination detection methods on small, quantized on-device LLMs, questioning whether rankings established on 7B-70B research models with ample sampling budgets hold in practice.
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-16 05:00 · arXiv cs.AI
Does the Ranking Hold? A Practitioner-Facing Audit of Hallucination Detectors on Small, Quantized, On-Device LLMs