作者位次 #2/5ACL 2026Findings· Findings of ACL
Fine-Grained Detection of Context-Grounded Hallucinations Using LLM s
Yehonatan Peisakhovsky · Zorik Gekhman · Yosi Mass · Liat Ein-Dor · Roi Reichart
摘要
Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing complex evaluation pipelines. In the absence of established...