利用大模型生成结果的不一致性检测幻觉片段，无需额外训练。
keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection
- 通过分析随机采样响应的差异性识别幻觉段落
- 基于熵度量实现高精度幻觉检测，效果优于基线方法
- 适用于多语言场景，适合需要低成本部署的实践者
在黑箱语言模型生成文本中识别幻觉片段对实际应用至关重要。2025年SemEval任务3（Mu-SHROOM）提出了一项多语言幻觉与相关过生成错误共享任务。本文提出一种基于大模型不确定性检测幻觉的方法，核心假设是：若模型对某事实确信，则其多次采样输出一致；而幻觉内容会产生不同且矛盾的响应。我们通过熵值分析量化这种差异，实现幻觉段落的精准定位。该方法无需额外训练，成本低、可迁移性强。此外，我们进行了全面超参数调优与误差分析，深入揭示了模型行为特征。
原文摘要 · Abstract (English)
Identification of hallucination spans in black-box language model generated text is essential for applications in the real world. A recent attempt at this direction is SemEval-2025 Task 3, Mu-SHROOM-a Multilingual Shared Task on Hallucinations and Related Observable Over-generation Errors. In this work, we present our solution to this problem, which capitalizes on the variability of stochastically-sampled responses in order to identify hallucinated spans. Our hypothesis is that if a language model is certain of a fact, its sampled responses will be uniform, while hallucinated facts will yield different and conflicting results. We measure this divergence through entropy-based analysis, allowing for accurate identification of hallucinated segments. Our method is not dependent on additional training and hence is cost-effective and adaptable. In addition, we conduct extensive hyperparameter tuning and perform error analysis, giving us crucial insights into model behavior.
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。