幻觉作为承诺失败：更大的LLM在知道答案的情况下仍会出错
Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
AI总结：
本文研究了大型LLM在知道正确答案的情况下仍出现幻觉的现象，发现模型在生成答案时，正确概念的概率分布方式决定了幻觉的发生，而非是否包含正确概念。
摘要：
幻觉通常被视为知识缺失的直接后果：当正确答案不在生成时的分布中，模型会错误回答；当正确答案存在时，模型会正确回答。我们通过引入一个语义上的答案可用性概念，聚合表达相同答案概念的token级变体，检验这一假设。在Qwen和Llama模型（0.8B至72B，包括Instruct和Base版本）中，16-47%的Instruct幻觉在模型承诺回答时已有显著概率质量在正确概念上，且随着规模增加，此比例单调上升。将此类失败与具有匹配语义支持的正确生成进行比较，发现区别不在于是否表示正确概念，而在于概率分布方式：正确生成将质量集中于单一表层形式，幻觉则将其分散到多个替代选项中。这种锐化不对称性在多token生成中也延伸，并在预生成隐藏状态中可检测到。这些结果识别出单一机制：指令微调通过规模锐化答案承诺，使有用性和自信幻觉成为同一底层倾向的两种结果。
英文摘要：
Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectly when the correct answer is absent from its generation-time distribution, and correctly when it is present. We test this assumption by introducing a semantic notion of answer availability that aggregates token-level variants expressing the same answer concept, and asks whether the correct concept is already available at the moment the model commits to an answer. Across Qwen and Llama models from 0.8B to 72B in both Instruct and Base variants, 16-47% of Instruct hallucinations occur with substantial probability mass already on the correct concept, and the rate rises monotonically with scale. Comparing such failures against correct generations with matched semantic support, the distinguishing factor is not whether the correct concept is represented, but how its probability is distributed: correct generations concentrate mass on a single surface form, hallucinations disperse it across alternatives. The same sharpening asymmetry extends across multi-token generation and is detectable in pre-generation hidden states. Together, these results identify a single mechanism: instruction tuning sharpens answer commitment with scale, making helpfulness and confident hallucination two consequences of the same underlying disposition.
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。
