135
0
v1v2 (latest)

Think-to-Talk or Talk-to-Think? When LLMs Come Up with an Answer in Multi-Step Arithmetic Reasoning

Abstract

This study investigates the internal reasoning process of language models during arithmetic multi-step reasoning, motivated by the question of when they internally form their answers during reasoning. Particularly, we inspect whether the answer is determined before or after chain-of-thought (CoT) begins to determine whether models follow a post-hoc Think-to-Talk mode or a step-by-step Talk-to-Think mode of explanation. Through causal probing experiments in controlled arithmetic reasoning tasks, we found systematic internal reasoning patterns across models in our case study; for example, single-step subproblems are solved before CoT begins, and more complicated multi-step calculations are performed during CoT.

View on arXiv
@article{kudo2025_2412.01113,
  title={ Think-to-Talk or Talk-to-Think? When LLMs Come Up with an Answer in Multi-Step Arithmetic Reasoning },
  author={ Keito Kudo and Yoichi Aoki and Tatsuki Kuribayashi and Shusaku Sone and Masaya Taniguchi and Ana Brassard and Keisuke Sakaguchi and Kentaro Inui },
  journal={arXiv preprint arXiv:2412.01113},
  year={ 2025 }
}
Comments on this paper

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.