通过知识神经元揭示大语言模型的事实回忆行为
Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons
AI总结：
本文通过知识神经元分析大语言模型在推理中的事实回忆行为，发现模型常走捷径而忽略关键事实，并证明增强事实回忆可提升推理性能，思维链提示能强化有序推理与事实检索。
摘要：
本文研究大语言模型（LLMs）在面对推理任务时是否主动回忆或检索其内部存储的事实知识。通过知识神经元对LLMs在每个推理步骤中的内部事实回忆进行分析，我们揭示出LLMs在某些情况下未能利用关键的事实关联，而是倾向于选择替代性的、类似捷径的路径来回答推理问题。通过人工操控LLMs中参数化知识的回忆过程，我们证明增强这一回忆过程能够直接提升推理性能，而抑制该过程则会导致显著退化。此外，我们评估了思维链（CoT）提示这一用于处理复杂推理任务的强大技术的效果。我们的发现表明，CoT可以通过鼓励LLMs进行有序且可靠的推理来强化事实知识的回忆。进一步地，我们探究了上下文冲突如何在推理过程中影响事实的检索，以全面理解LLMs的事实回忆行为。代码和数据将很快公开。
英文摘要：
In this paper, we investigate whether Large Language Models (LLMs) actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks. Through an analysis of LLMs' internal factual recall at each reasoning step via Knowledge Neurons, we reveal that LLMs fail to harness the critical factual associations under certain circumstances. Instead, they tend to opt for alternative, shortcut-like pathways to answer reasoning questions. By manually manipulating the recall process of parametric knowledge in LLMs, we demonstrate that enhancing this recall process directly improves reasoning performance whereas suppressing it leads to notable degradation. Furthermore, we assess the effect of Chain-of-Thought (CoT) prompting, a powerful technique for addressing complex reasoning tasks. Our findings indicate that CoT can intensify the recall of factual knowledge by encouraging LLMs to engage in orderly and reliable reasoning. Furthermore, we explored how contextual conflicts affect the retrieval of facts during the reasoning process to gain a comprehensive understanding of the factual recall behaviors of LLMs. Code and data will be available soon.
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。
