BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
Junxiao Yang · Jinzhe Tu · Haoran Liu · Xiaoce Wang · Chujie Zheng · Zhexin Zhang · Shiyao Cui · Caishun Chen · Tiantian He · Hongning Wang · Yew-Soon Ong · Minlie Huang
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Junxiao Yang · Jinzhe Tu · Haoran Liu · Xiaoce Wang · Chujie Zheng · Zhexin Zhang · Shiyao Cui · Caishun Chen · Tiantian He · Hongning Wang · Yew-Soon Ong · Minlie Huang
Binghai Wang · Yantao Liu · Yuxuan Liu · Tianyi Tang · Shenzhi Wang · Chang Gao · Chujie Zheng · Yichang Zhang · Le Yu · Shixuan Liu · Tao Gui · Qi Zhang · Xuanjing Huang · Bowen Yu · Fei Huang · Junyang Lin
Generative Reward Models (GenRMs) and LLM-as-a-Judge exhibit deceptive alignment by producing correct judgments for incorrect reasons, as they are trained and evaluated to prioritize Outcome Accuracy , which undermines their ability to generalize during RLHF. We introduce Rationale Consistency ,...