4 papers · 1 filter
Robust Post-Training for Generative Recommenders: Why Exponential Reward-Weighted SFT Outperforms RLHF
Keertana Chidambaram, Sanath Kumar Krishnamurthy, Qiuling Xu +2
Aligning generative recommender systems to user preferences via post-training is critical for closing the gap between next-item prediction and actual recommendation quality. Existi…
Personalized Adaptation via In-Context Preference Learning
Allison Lau, Younwoo Choi, Vahid Balazadeh +3
Reinforcement Learning from Human Feedback (RLHF) is widely used to align Language Models (LMs) with human preferences. However, existing approaches often neglect individual user p…
Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
Keertana Chidambaram, Karthik Vinay Seetharaman, Vasilis Syrgkanis
Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference…
Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity
Vahid Balazadeh, Keertana Chidambaram, Viet Nguyen +2
We study the problem of online sequential decision-making given auxiliary demonstrations from experts who made their decisions based on unobserved contextual information. These dem…