Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts
Manjiang Yu, Hongji Li, Zihan Wang +5
Linear probing and activation steering use linear directions to predict and control behavior-level concepts such as correctness, safety, and social bias in question answering. We c…
cs.CL2025
Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
Hongji Li, Junchi yao, Manjiang Yu +4
Machine unlearning aims to erase requested data from trained models without full retraining. For Reasoning Multimodal Large Language Models (RMLLMs), this is uniquely challenging:…