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.

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.

In the rapidly evolving field of artificial intelligence, Large Language Models (LLMs) have emerged as a pivotal component [45]. Their ability to understand, generate, and manipulate human language has opened up new avenues towards advanced machine intelligence. Interestingly, despite being primarily trained on next-token prediction tasks, LLMs are able to produce much more sophisticated answers when asked to generate steps of reasoning [30, 58]. This phenomenon, often referred to as Chain-of-Thought (CoT) reasoning, and illustrated on Table 1, appears paradoxical: on the one hand, LLMs are not explicitly programmed to reason; on the other hand, they are capable of following logical chains of thoughts to produce relatively complex answers. Table 1: Chain-of-Thought consists in eliciting reasoning steps before answering (A) a question (Q).