Real-Time Detection of Hallucinated Entities in Long-Form Generation — mentioned by robrenaud

Fri, 21 Nov 2025 07:37:05 GMT

LLMs do have some internal representations that predict pretty well when they are making stuff up. https://arxiv.org/abs/2509.03531v1 - We present a cheap, scalable method for real-time identification of hallucinated tokens in long-form generations, and scale it effectively to 70B parameter models. Our approach targets \emph{entity-level hallucinations} -- e.g., fabricated names, dates, citations -- rather than claim-level, thereby naturally mapping to token-level labels and enabling streaming detection. We develop an annotation methodology that leverages web search to annotate model…

Paper and discussion history. A mention is not an endorsement.

Real-Time Detection of Hallucinated Entities in Long-Form Generation · HackerPapers discussions

Real-Time Detection of Hallucinated Entities in Long-Form Generation — mentioned by robrenaud