Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts
Yibin Lou, Yi Hu, Jianhui Chen +3
Large Language Models (LLMs) frequently encounter conflicts between internal parametric knowledge and external contextual knowledge, yet the mechanisms governing this selection rem…
cs.CL2026
Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods
Haotian Yang, Huikang Jiang, Yucheng Wu +4
Activation steering provides a lightweight and flexible way to control large language model (LLM) behavior. However, effective steering requires more than inducing the intended beh…