Findings of the Association for Computational Linguistics: EMNLP 2025 / 奖励驱动进化

Self-ensemble: Mitigating Confidence Distortion for Large Language Models

作者：Zicheng Xu, Guanchu Wang, Guangyao Zheng, Yu-Neng Chuang, Alexander Szalay, Xia Hu, Vladimir Braverman · 单位：Rice University, University of North Carolina at Charlotte, Johns Hopkins University · 会议/期刊：Findings of the Association for Computational Linguistics: EMNLP 2025 · 方向：奖励驱动进化 · 发布日期：2025-06-02

自我进化智能体奖励驱动进化大语言模型智能体奖励学习强化学习
新标签打开 AlphaXiv新标签打开 Code
Self-ensemble: Mitigating Confidence Distortion for Large Language Models figure
AlphaXiv 中文概览（可滚动查看）