一作ICLR 2026Poster· Deep Learning / Everything Else
Aligning Deep Implicit Preferences by Learning to Reason Defensively
Peiming Li · Zhiyuan Hu · Shiyu Li · Xi Chen · Yang Tang
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。
Peiming Li · Zhiyuan Hu · Shiyu Li · Xi Chen · Yang Tang
Yifan Wang · Shiyu Li · Peiming Li · Xiaochen Yang · Zheng Wei · Yang Tang
Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning, its verbosity imposes substantial computational overhead. Recent works often focus exclusively on outcome alignment...