作者位次 #3/12ACL 2026Poster· Natural Language Processing
Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics
Ziwen Xu · Chenyan WU · Hengyu Sun · Haiwen Hong · Mengru Wang · Yunzhi Yao · Longtao Huang · Hui Xue · Shumin Deng · Zhixuan Chu · Huajun Chen · Ningyu Zhang
摘要
Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interventions, are often studied in isolation, obscuring their connections and making comparison difficult. In this work, we present a unified view that frames the...