一作ICLR 2026Poster· Social Aspects / Trustworthy Machine Learning
General Exploratory Bonus for Optimistic Exploration in RLHF
Wendi Li · Changdae Oh · Sharon Li
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。
Wendi Li · Changdae Oh · Sharon Li
Changdae Oh · Seongheon Park · To Eun Kim · Jiatong Li · Wendi Li · Samuel Yeh · Sean Du · Hamed Hassani · Paul Bogdan · Dawn Song · Sharon Li
Uncertainty quantification (UQ) for large language models (LLMs) is a key building block for safety guardrails of daily LLM applications. Yet, even as LLM agents are increasingly deployed in highly complex tasks, most UQ research still centers on single-turn question-answering. We argue that UQ r...
Wendi Li · Sharon Li
Current reinforcement learning objectives for large-model reasoning primarily focus on maximizing expected rewards. This paradigm can lead to overfitting to dominant reward signals, while neglecting alternative yet valid reasoning trajectories, thereby limiting diversity and exploration. To addre...