HACK：沿确定性与知识轴的幻觉现象
HACK: Hallucinations Along Certainty and Knowledge Axes
AI总结：
该研究提出HACK框架，沿知识、确定性两条轴对大语言模型幻觉分类，通过模型专属数据集构建、引导缓解法验证分类有效性，识别出高风险的确定性幻觉类型并提出新评估指标，呼吁研发针对性幻觉缓解方案。
摘要：
大语言模型（LLM）中的幻觉问题是其可靠应用的关键阻碍。现有研究通常依据幻觉的外部属性对其分类，而非基于LLM的内在属性，这种外部导向的研究忽略了一点：不同机制引发的幻觉可能需要针对性的缓解策略。我们提出一个沿知识、确定性两条轴对幻觉进行分类的框架。由于参数化知识和确定性可能因模型而异，我们的分类方法包含一个模型专属的数据集构建流程，用于区分不同类型的幻觉。在知识轴上，我们区分了由知识缺失导致的幻觉，以及模型虽具备正确答案相关知识却仍出现的幻觉。为验证框架的知识轴分类有效性，我们采用了引导缓解法（steering mitigation）——该方法依赖参数化知识的存在来调控模型激活值。通过证明两类幻觉间存在显著差异，我们填补了现有知识分类验证方法的空白。我们进一步分析了不同模型间独特的知识与幻觉模式，表明即便参数化知识相同，仍会出现不同类型的幻觉。转向确定性轴，我们识别出一类尤其值得关注的幻觉子集：模型内部虽具备正确知识，却带着确定性生成幻觉内容。我们提出一种新的评估指标，用于衡量缓解方法对该类幻觉的处理效果，结果显示部分方法虽平均表现良好，但在这类关键案例上的失效比例远超预期。我们的研究结果凸显了在幻觉分析中同时考虑知识与确定性的重要性，并呼吁研发基于幻觉潜在成因的针对性缓解方案。
英文摘要：
Hallucinations in LLMs present a critical barrier to their reliable usage. Existing research usually categorizes hallucination by their external properties rather than by the LLMs' underlying internal properties. This external focus overlooks that hallucinations may require tailored mitigation strategies based on their underlying mechanism. We propose a framework for categorizing hallucinations along two axes: knowledge and certainty. Since parametric knowledge and certainty may vary across models, our categorization method involves a model-specific dataset construction process that differentiates between those types of hallucinations. Along the knowledge axis, we distinguish between hallucinations caused by a lack of knowledge and those occurring despite the model having the knowledge of the correct response. To validate our framework along the knowledge axis, we apply steering mitigation, which relies on the existence of parametric knowledge to manipulate model activations. This addresses the lack of existing methods to validate knowledge categorization by showing a significant difference between the two hallucination types. We further analyze the distinct knowledge and hallucination patterns between models, showing that different hallucinations do occur despite shared parametric knowledge. Turning to the certainty axis, we identify a particularly concerning subset of hallucinations where models hallucinate with certainty despite having the correct knowledge internally. We introduce a new evaluation metric to measure the effectiveness of mitigation methods on this subset, revealing that while some methods perform well on average, they fail disproportionately on these critical cases. Our findings highlight the importance of considering both knowledge and certainty in hallucination analysis and call for targeted mitigation approaches that consider the hallucination underlying factors.
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。
