一作ACL 2026Poster· Natural Language Processing
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
Hao Mi · Qiang Sheng · Shaofei Wang · Beizhe Hu · Yifan Sun · Zhengjia Wang · Hengqi Zeng · Yang Li · Danding Wang · Juan Cao
摘要
Large Language Models (LLMs) are prone to factual hallucinations, risking their reliability in real-world applications. Existing hallucination detectors mainly extract micro-level intrinsic patterns for uncertainty quantification or elicit macro-level self-judgments through verbalized prompts. Ho...