Large language model (LLM) personalization aims to generate responses that align with individual user preferences, making accurate preference inference critical. In practice, user-LLM interaction histories naturally contain rich preference signals. However, extracting preferences from these histories remains underexplored and challenging: the history can be long and noisy, preferences may evolve over time, and preferences may vary across situations even within the same topic. To address these challenges, we develop PREFINFER, a model that accurately infers user preferences from the user’s interaction history with an LLM. Specifically, we introduce PREFMINE, an automated data construction method that synthesizes high-quality preference inference data, where each sample includes a synthetic interaction history, a current user request, and the user’s preference for the current request, and construct PREFMINE-15K for training PREFINFER. Experiments show that PREFINFER achieves advanced performance on preference inference, and the preferences inferred by PREFINFER effectively guide LLMs to generate responses better aligned with user preferences. We conduct thorough ablation studies on the key design choices of PREFMINE, validating their effectiveness. We have released the code, data, and models to facilitate further research(https://github.com/THU-KEG/PREFINFER).