作者位次 #2/6ICLR 2026Poster· Reinforcement Learning / Multi-agent
GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
Divij Handa · Mihir Parmar · Aswin RRV · Md Nayem Uddin · Hamid Palangi · Chitta Baral
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。
Divij Handa · Mihir Parmar · Aswin RRV · Md Nayem Uddin · Hamid Palangi · Chitta Baral
Ruiyao Xu · Mihir Parmar · Tiankai Yang · Zhengyu Hu · Yue Zhao · Kaize Ding
Learning from preference-based feedback has become an effective approach for aligning LLMs across diverse tasks. However, high-quality human-annotated preference data remains expensive and scarce. Existing methods address this challenge through either self-rewarding, which scales by using purely...