Jiachen Zhao

Authors: Jiachen Zhao, Yiyou Sun, Weiyan Shi, Dawn Song > Are LLMs truly reasoning step by step in their Chain-of-Thought — or just performing it? TL;DR: We analyze the causal contribution of each reasoning step in a Chain-of-Thought (CoT) to evaluate its faithfulness with respect to the model’s final prediction....

TL;DR: We present causal evidence that LLMs encode harmfulness and refusal separately. Notably, we find that a model may internally judge an instruction to be harmless, yet still refuse it. While prior work has primarily focused on refusal behaviors and identified a single refusal direction, we uncover a distinct dimension...