作者位次 #3/5ACL 2026Findings· Findings of ACL
Beyond Output Confidence: Epistemic-Aware Hallucination Detection with Answer-Level Signals
Jieran Li · Xiuyuan Hu · Yang Zhao · Dongbiao Sun · Hao Zhang
摘要
Despite their strong generative capabilities, large language models frequently exhibit hallucinations, particularly due to outside-boundary confidence where incorrect assertions are produced with high statistical certainty. Existing approaches commonly use output probability as a proxy for truthf...