The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates 文章
ArXiv CS.CL2026-05-28NEWSen作者: Shaobo Wang, Guo Chen, Ziyue Wang, Zhengyang Tang, Qingyang Liu, Xingzhang Ren, Dayiheng Liu, Linfeng Zhang