Chain-of-Thought Tokens are Computer Program Variables

ACL ARR 2025 May Submission211 Authors

Abstract:

Chain-of-thoughts (CoT) instructs large language models (LLMs) to generate intermediate steps before reaching the final answer, and has been proven effective to help LLMs solve complex reasoning tasks.
However, the inner mechanism of CoT still remains largely unclear.
In this paper, we empirically study the role of CoT tokens in LLMs on two compositional tasks: multi-digit multiplication and dynamic programming.
While CoT is essential for solving these problems, we find that preserving only tokens that store intermediate results would achieve comparable performance.
Furthermore, we observe that storing intermediate results in an alternative latent form will not affect model performance.
We also randomly intervene some values in CoT, and notice that subsequent CoT tokens and the final answer would change correspondingly.
These findings suggest that CoT tokens function like variables in computer programs, but with potential drawbacks like unintended shortcuts and computational complexity limits between tokens.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: chain-of-thought

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 211