大语言模型是怀疑论者：输入冲突型幻觉的假阴性问题
Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination
AI总结：
该研究发现大语言模型存在假阴性偏差（输入冲突型幻觉的一种），即评估陈述时倾向否定且过度自信，同时验证了上下文调整与查询改写可有效缓解该问题。
摘要：
本文识别出一类会引发输入冲突型幻觉的新型偏差，即大语言模型（LLMs）生成的回复与输入上下文内容不一致。我们将这一问题称为假阴性问题，指的是LLMs在根据上下文评估陈述正确性时，倾向于返回否定判断的现象。在针对包含相同信息但事实方向相反的陈述对开展的实验中，我们观察到LLMs表现出假阴性偏差，具体而言，模型在回复“False（错误）”时会表现出更强的过度自信。此外，我们分析了假阴性问题与上下文、查询改写的关系，发现这两种方式都能有效解决LLMs中的假阴性问题。
英文摘要：
In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context. This issue we have termed the false negative problem refers to the phenomenon where LLMs are predisposed to return negative judgments when assessing the correctness of a statement given the context. In experiments involving pairs of statements that contain the same information but have contradictory factual directions, we observe that LLMs exhibit a bias toward false negatives. Specifically, the model presents greater overconfidence when responding with False. Furthermore, we analyze the relationship between the false negative problem and context and query rewriting and observe that both effectively tackle false negatives in LLMs.
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。
