← Search

Changshuo Shen

2 accepted papers

2026

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint

ICLR 2026poster

As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an effective approach for enhancing LLM safety by adding a refusal dire…

Cited by 0SourcecodeScholar
2025

On Reasoning Strength Planning in Large Reasoning Models

NeurIPS 2025poster

Recent studies empirically reveal that large reasoning models (LRMs) can automatically allocate more reasoning strengths (\ie the number of reasoning tokens) for harder problems, exhibiting difficulty-awareness for better task performance. While this automatic reasoning strength allocation phenomeno…

Cited by 0SourcecodeScholar