HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization

2026-09-09

AI Summary

为解决在线个性化语言模型中长期偏好与短期需求难以调和的问题，提出HyperTrace框架，通过假设驱动的偏好追踪方法实现无需训练的个性化。

Abstract

Personalized language models aim to adapt responses to individual users, whose preferences are often latent and revealed gradually through interaction. Existing training-free methods rely on stored histories or retrieved memories, but they often struggle to reconcile long- term preferences with short-term topic-specific needs. To address this issue, we propose HyperTrace, a training-free framework that formulates online personalization as latent preference tracing. HyperTrace maintains interpretable natural-language hypotheses over short-term intent and long-term preferences, and updates them through an SMC-style reweight process using an LLM-based surrogate choice model. By updating these hypotheses across turns and sessions, HyperTrace enables personalization without parameter updates. Experiments on PRISM and PersonaMem-v2 show that HyperTrace improves response alignment, preference prediction, and profile consistency over strong online baselines, demonstrating the effectiveness of tracing latent user preferences for robust personalization. Code and scripts are available in the repository: https://github.com/jiseshen/HyperTrace.

Problem

• personalized language models
• latent preferences
• short-term needs
• online personalization
• preference tracing

Innovation

• latent preference tracing
• training-free framework
• SMC-style reweight process
• LLM-based surrogate choice model