ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning.
Xuan Xiong, Huan Liu, Li Gu, Zhixiang Chi, Yue Qiu, Yuanhao Yu, Yang Wang
Browse the full ACL paper archive.
Xuan Xiong, Huan Liu, Li Gu, Zhixiang Chi, Yue Qiu, Yuanhao Yu, Yang Wang
Browse the full ACL paper archive.