Cold-start personalization requires inferring preferences from minimal interaction when no user-specific historical data is available. The space of possible preferences is vast, yet users care about only a sparse subset and rarely articulate them upfront; combined with limited interaction budgets, this makes preference elicitation challenging. Our key insight is that preferences exhibit predictable structure across populations; e.g., users who want detailed explanations often also value worked examples. We propose CAPE (Cold-start Adaptive Preference Elicitation), which learns a structured world model of preference correlations offline from complete profiles, then performs training-free Bayesian inference online to select informative questions and predict complete preference profiles, including dimensions never asked about. Even simple belief model instantiations (e.g., linear regression) substantially outperform end-to-end RL. Across medical, mathematical, social, and commonsense reasoning, CAPE achieves 80.8% alignment with ground-truth user preferences versus 68.5% for RL, requires 2.5x to over 15x fewer interactions, and adapts its questions twice as often as RL. Our contribution is a principled decomposition of cold-start personalization that makes Bayesian preference elicitation practical at scale for LLM systems.
Sparse Personalized Text Generation with Multi-Trajectory Reasoning
Department of Computer Science, Vanderbilt University, Nashville, Tennessee(范德比尔特大学计算机科学系);Adobe Research, San Jose, California(Adobe研究);University of Orgeon, Eugene, Oregon(奥尔戈恩大学)
T-POP: Test-Time Personalization with Online Preference Feedback
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));East China Normal University(华东师范大学);Shenzhen Loop Area Institute(深圳河套学院);Tianjin University(天津大学);The Chinese University of Hong Kong(香港中文大学);Beihang University(北京航空航天大学);City University of Hong Kong(香港城市大学);The Hong Kong University of Science and Technology (Guangzhou)(香港理工大学(广州))
Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));University of Copenhagen(哥本哈根大学);City University of Hong Kong(香港城市大学);East China Normal University(华东师范大学)
Personalized Graph-Based Retrieval for Large Language Models
University of California Santa Cruz(加州大学圣克ruz分校);Meta AI;Adobe Research(Adobe研究);University of Oregon(俄勒冈大学);University of Southern California(南加州大学);Cisco AI Research(思科人工智能研究)
Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning
Institute of Engineering Research, Korea University(韩国大学工程研究所);Kim Jaechul Graduate School of AI, KAIST(韩国科学技术院金在哲人工智能研究生院);Industrial Management Engineering, Korea University(韩国大学产业管理工程学院)