一作ICLR 2026Poster· Applications / Language, Speech and Dialog
Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond
Dingzirui Wang · Xuanliang Zhang · Keyan Xu · Qingfu Zhu · Wanxiang Che · Yang Deng
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。
Dingzirui Wang · Xuanliang Zhang · Keyan Xu · Qingfu Zhu · Wanxiang Che · Yang Deng
Dingzirui Wang · Xuanliang Zhang · Rongyu Cao · Longxu Dou · Xianzhen Luo · YINGWEI MA · Qingfu Zhu · Binhua Li · Fei Huang · Yongbin Li
Generating and voting multiple answers is an effective method to mitigate reasoning inconsistencies of large language models (LLMs). Prior works have shown that multiple reasoning formats outperform a single format when generating multiple answers. However, previous works using multiple formats r...