LLM生成答案的片段级幻觉检测
Span-Level Hallucination Detection for LLM-Generated Answers
AI总结：
本文提出片段级幻觉检测框架，集成SRL分解答案为原子角色，用DeBERTa蕴含模型和token级置信度检测幻觉，在Mu-SHROOM数据集表现优异。
摘要：
检测LLM生成答案中的幻觉片段对于提高事实一致性至关重要。本文提出了一个用于SemEval-2025共享任务的片段级幻觉检测框架，专注于英语和阿拉伯语文本。我们的方法集成了语义角色标注（SRL）将答案分解为原子角色，然后将其与通过基于问题的LLM提示获取的检索参考上下文进行比较。使用基于DeBERTa的文本蕴含模型，我们评估每个角色与检索上下文的语义对齐。蕴含分数通过从输出logits派生的令牌级置信度度量进一步细化，组合分数用于检测幻觉片段。在Mu-SHROM数据集上的实验显示了竞争性能。此外，通过提示GPT-4和LLaMA进行事实核查验证了幻觉片段。我们的发现有助于改进LLM生成响应中的幻觉检测。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
