Score: 0

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?

Published: August 27, 2025 | arXiv ID: 2508.19827v1

By: Samuel Lewis-Lim , Xingwei Tan , Zhixue Zhao and more

Potential Business Impact:

Makes AI think more honestly about hard problems.

Business Areas:
Artificial Intelligence Artificial Intelligence, Data and Analytics, Science and Engineering, Software

Recent work has demonstrated that Chain-of-Thought (CoT) often yields limited gains for soft-reasoning problems such as analytical and commonsense reasoning. CoT can also be unfaithful to a model's actual reasoning. We investigate the dynamics and faithfulness of CoT in soft-reasoning tasks across instruction-tuned, reasoning and reasoning-distilled models. Our findings reveal differences in how these models rely on CoT, and show that CoT influence and faithfulness are not always aligned.

Country of Origin
🇬🇧 United Kingdom

Page Count
16 pages

Category
Computer Science:
Artificial Intelligence