Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models

2026-09-08

AI Summary

研究通过ENOUGH方法构建最小充分用户画像，以减少冗余并提高个性化语言模型的效率和效果。

Abstract

Retrieval-augmented personalization enables large language models to produce more accurate and preference-aligned outputs using relevant records retrieved from user histories. Personalized language models typically prepend a fixed number of retrieved user records, even when additional history is redundant, harmful, or unrelated to a user's distinctive behavior. We study minimal sufficient personalization: constructing the least costly ordered profile for each input while preserving the utility achievable from a retrieved candidate pool. We introduce ENOUGH, a method that iteratively appends behavioral records or emits STOP to construct profiles with adaptive lengths. Offline, bounded counterfactual search evaluates profile prefixes by jointly considering downstream gains, user specificity, and token costs. The resulting long-horizon targets are distilled into a multi-head value controller with explicit ranking and stopping supervision. At inference, the controller selects and orders records through lightweight decisions, and the frozen generator is invoked once after stopping. Extensive experiments on six personalized tasks demonstrate that ENOUGH consistently outperforms strong heuristic and retrieval-augmented baselines in both effectiveness and efficiency, achieving minimal sufficient profiles that preserve personalization utility while reducing unnecessary context costs.

Problem

• minimal sufficient personalization
• user profiles
• retrieval-augmented personalization
• language models

Innovation

• minimal sufficient personalization
• ENOUGH method
• adaptive lengths
• bounded counterfactual search
• multi-head value controller