AI RESEARCH
Where Do Reasoning Models Refuse?
arXiv CS.AI
•
ArXi:2507.03167v3 Announce Type: replace-cross Chat models without chain-of-thought (CoT) reasoning must decide whether to refuse a harmful request before generating their first response token. Reasoning models, by contrast, produce extended chains of thought before their final output, raising a natural question: where in this process does the decision to refuse occur? We investigate this across four open-source reasoning models.