FSPO: Few-Shot Preference Optimization of Synthetic Preference Data Elicits LLM Personalization to Real Users

Effective personalization of LLMs is critical for a broad range of user-interfacing applications such as virtual assistants and content curation. Inspired by the strong in-context learning capabilities of LLMs, we propose few-shot preference optimization (FSPO), an algorithm for LLM personalization that reframes reward modeling as a meta-learning problem. Under FSPO, an LLM learns to quickly infer a personalized reward function for a user via a few labeled preferences. Since real-world preference data is scarce and challenging to collect at scale, we propose careful design choices to construct synthetic preference datasets for personalization, generating over 1M synthetic personalized preferences using publicly available LLMs. In particular, to successfully transfer from synthetic data to real users, we find it crucial for the data to exhibit both high diversity and coherent, self-consistent structure. We evaluate FSPO on personalized open-ended generation for up to 1,500 synthetic users across three domains: movie reviews, pedagogical adaptation based on educational background, and general question answering. We also run a controlled human study. Overall, FSPO achieves an 87% Alpaca Eval winrate in generating responses that are personalized to synthetic users and a 72% winrate with real human users in open-ended question answering.