WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior
arXiv:2603.18474v1 Announce Type: new Abstract: Precise behavioral control of large language models (LLMs) is critical for complex applications. However, existing methods often incur high training …
Haonan Yu, Junhao Liu, Zhenyu Yan, Haoran Lin, Xin Zhang
8 views
