Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability
Xu Wang, Difan Zou, Xuansheng Wu
Reliable refusal of harmful requests is essential to the safe deployment of language models. Because excessive eagerness to please users may undermine existing refusal capabilities…
cs.CL2025
Investigating CoT Monitorability in Large Reasoning Models
Shu Yang, Junchao Wu, Xilin Gong +4
Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks by engaging in extended reasoning before producing final answers. Beyond improving abilities…
cs.CL2025
Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs
Shu Yang, Junchao Wu, Xuansheng Wu +3
Large Reasoning Models (LRMs) have achieved remarkable performance on complex tasks by engaging in extended reasoning before producing final answers, yet this strength introduces t…