4 papers
LLMs Encode Harmfulness and Refusal Separately
Jiachen Zhao, Jing Huang, Zhengxuan Wu +2
LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by…
Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal
Kia-Jüng Yang, Dominik Meier, Jiachen Zhao +2
Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms suc…
Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought
Jiachen Zhao, Yiyou Sun, Weiyan Shi +1
Large language models can generate long chain-of-thought (CoT) reasoning, yet prior work suggests that CoT can be post-hoc rationalization rather than a faithful reflection of the…
PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models
Jiyuan An, Jiachen Zhao, Fan Chen +6
The construction of CAD models has traditionally relied on labor-intensive manual operations and specialized expertise. Recent advances in large language models (LLMs) have inspire…