arXiv cs.CL· Avinandan Bose, Shuyue Stella Li, Faeze Brahman, Pang Wei Koh, Simon Shaolei Du, Yulia Tsvetkov, Maryam Fazel, Lin Xiao, Asli Celikyilmaz·· 10 小时前AI 评分31
CAPE：用贝叶斯自适应提问实现冷启动个性化
Cold-Start Personalization via Bayesian Adaptive Questioning
AI 导读
CAPE（Cold-start Adaptive Preference Elicitation）通过离线学习偏好相关性的结构化世界模型、在线做免训练贝叶斯推理来选问题并补全用户偏好画像。在医学、数学、社交与常识推理任务上，其偏好对齐率达 80.8%，RL 为 68.5%，交互次数减少 2.5 倍至 15 倍以上，提问调整频率是 RL 的两倍。
正文 · 原文
Abstract: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.
| Comments: | 26 pages, 4 figures, 10 tables |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2602.15012 [cs.CL] |
| (or arXiv:2602.15012v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2602.15012 arXiv-issued DOI via DataCite |
Submission history
From: Shuyue Stella Li [view email]
[v1]
Mon, 16 Feb 2026 18:52:13 UTC (2,273 KB)
[v2]
Tue, 10 Nov 2026 03:29:41 UTC (1,992 KB)
来源：arXiv cs.CL · arxiv.org