Author

Yu-Chen Wu

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

CANS: Capability-Preserving Neuron Steering for Large Language Models

Activation steering offers training-free and dynamic control of target behaviors in large language models, but existing methods can impair general capabilities and require domain-specific intervention designs. We introduce Capability-Preserving Neuron Steering (CANS), a unified framework that balances target-behavior c...

Yu-Chen Wu, Cheng-Yi Xie, Chen-Peng Wang et al. · 0 citations

#natural language process... Preprint Oct 2026

Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods

Activation steering provides a lightweight and flexible way to control large language model (LLM) behavior. However, effective steering requires more than inducing the intended behavior: it should also limit unintended changes and remain robust across inputs and training data. Existing evaluations cover these dimension...

Hao-Tian Yang, Hui-Kang Jiang, Yu-Chen Wu et al. · 1 citation