通过语义角色分解与上下文匹配，精准定位大模型生成答案中的幻觉片段。
Span-Level Hallucination Detection for LLM-Generated Answers
- 将答案拆解为语义角色，逐角色比对检索到的参考文本。
- 在Mu-SHROOM数据集上表现优异，结合GPT-4与LLaMA验证了幻觉片段。
- 适用于需提升事实一致性的中文/阿拉伯语文本生成场景。
检测大模型生成答案中幻觉段落对于提升事实一致性至关重要。本文针对SemEval-2025共享任务，提出一种面向英文与阿拉伯文的段级幻觉检测框架。方法基于语义角色标注（SRL）将答案分解为原子语义角色，并通过基于问题的大模型提示获取参考上下文。利用DeBERTa-based文本蕴含模型评估各角色与参考上下文的语义对齐度。通过输出logits计算的词级置信度进一步优化蕴含得分，最终联合判定幻觉段落。在Mu-SHROOM数据集上的实验表明性能具有竞争力。此外，通过调用GPT-4和LLaMA进行事实核查，确认了检测出的幻觉段落。研究成果有助于提升大模型生成回复的准确性。
原文摘要 · Abstract (English)
Detecting spans of hallucination in LLM-generated answers is crucial for improving factual consistency. This paper presents a span-level hallucination detection framework for the SemEval-2025 Shared Task, focusing on English and Arabic texts. Our approach integrates Semantic Role Labeling (SRL) to decompose the answer into atomic roles, which are then compared with a retrieved reference context obtained via question-based LLM prompting. Using a DeBERTa-based textual entailment model, we evaluate each role semantic alignment with the retrieved context. The entailment scores are further refined through token-level confidence measures derived from output logits, and the combined scores are used to detect hallucinated spans. Experiments on the Mu-SHROOM dataset demonstrate competitive performance. Additionally, hallucinated spans have been verified through fact-checking by prompting GPT-4 and LLaMA. Our findings contribute to improving hallucination detection in LLM-generated responses.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。