Iteration Head：思维链的机制研究
Iteration Head: A Mechanistic Study of Chain-of-Thought
AI总结：
本文在受控可解释的transformer设置中研究CoT推理的机制，发现并追踪负责迭代推理的iteration heads，同时评估其CoT技能的跨任务可迁移性。
摘要：
众所周知，Chain-of-Thought（CoT，思维链）推理在实证表现和理论近似能力两方面都能提升大型语言模型。然而，我们对CoT能力的内在运作方式及其出现条件的理解仍然有限。本文通过在受控且可解释的环境中展示CoT推理如何在transformer中涌现，帮助填补这一空白。具体而言，我们观察到一种专用于迭代推理的特殊注意力机制出现，并将其命名为“iteration heads（迭代头）”。我们将这些迭代头的涌现及其精确工作方式追踪到注意力层级，并衡量它们所产生的CoT技能在不同任务之间的可迁移性。
英文摘要：
Chain-of-Thought (CoT) reasoning is known to improve Large Language Models both empirically and in terms of theoretical approximation power. However, our understanding of the inner workings and conditions of apparition of CoT capabilities remains limited. This paper helps fill this gap by demonstrating how CoT reasoning emerges in transformers in a controlled and interpretable setting. In particular, we observe the appearance of a specialized attention mechanism dedicated to iterative reasoning, which we coined "iteration heads". We track both the emergence and the precise working of these iteration heads down to the attention level, and measure the transferability of the CoT skills to which they give rise between tasks.
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。
