
YC
Yizhuo Chen, Xin Liu, Ruijie Wang, Zheng Li, Pei Chen, Changlong Yu, Qingyu Yin, Priyanka Nigam, Meng Jiang, Bing Yin
· 1 min read
ResearcharXiv cs.CL
POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
arXiv:2510.17881v4 Announce Type: replace
Abstract: Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem into two components connected by a natural-language interface: a shared inference model that distills heterogeneous user signals into a concise preference summary, and a shared generator that conditions on this summary to produce personalized responses. Both components are trained under a unified preference-optimization objective, with reinforcement learning handling the non-differentiable inference step. This objective decomposes into generator approximation error and summary informativeness, revealing how a single loss simultaneously drives accurate generation and informative summarization. Because the interface is natural language, learned summaries can be inferred once per user and reused across different generators -- including frozen, black-box commercial APIs. Across four personalization benchmarks, POPI generally improves personalization quality while reducing context overhead by up to an order of magnitude.
Original source
This story was published by arXiv cs.CL and written by Yizhuo Chen, Xin Liu, Ruijie Wang, Zheng Li, Pei Chen, Changlong Yu, Qingyu Yin, Priyanka Nigam, Meng Jiang, Bing Yin. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


