作者位次 #5/5ICML 2026Poster· Deep Learning / Large Language Models
Normalized Rewards for Preference Optimization
Shawn Im · Federico Danieli · Skyler Seto · Barry-John Theobald · Katherine Metcalf
对齐与偏好OpenReview
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。
Shawn Im · Federico Danieli · Skyler Seto · Barry-John Theobald · Katherine Metcalf
Arnav Arora · Natalie Schluter · Katherine Metcalf · Maartje Ter Hoeve
Conversational Large Language Models are post-trained on language that expresses specific behavioural traits, such as curiosity, open-mindedness, and empathy, and values, such as helpfulness, harmlessness, and honesty. This is done to increase utility, ensure safety, and improve the user experien...