HyperTrace：基于假设的偏好追踪用于在线大语言模型个性化
HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization
浏览论文内容
中文总结 AI 辅助
HyperTrace提出免训练的在线个性化框架，通过自然语言假设追踪潜在偏好，利用SMC重加权更新，在PRISM和PersonaMem-v2上提升响应对齐与偏好预测。
中文摘要 AI 辅助
个性化语言模型旨在使响应适应个体用户，而用户的偏好通常是潜在的，并通过交互逐步显现。现有的免训练方法依赖于存储的历史记录或检索到的记忆，但它们往往难以协调长期偏好与短期特定主题需求之间的矛盾。为解决这一问题，我们提出了HyperTrace，一个免训练框架，将在线个性化形式化为潜在偏好追踪。HyperTrace维护关于短期意图和长期偏好的可解释自然语言假设，并通过基于大语言模型的替代选择模型，采用序贯蒙特卡洛（SMC）风格的重加权过程来更新这些假设。通过跨轮次和会话更新这些假设，HyperTrace实现了无需参数更新的个性化。在PRISM和PersonaMem-v2上的实验表明，HyperTrace在响应对齐、偏好预测和画像一致性方面优于强在线基线，证明了追踪潜在用户偏好对于稳健个性化的有效性。代码和脚本可在该仓库中获取：https://this URL。
英文摘要
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.
发表机构
- Johns Hopkins University（约翰斯·霍普金斯大学）
- Institute of Science Tokyo（东京科学大学）
- NYU Tandon（纽约大学坦登工程学院）
- NYU Abu Dhabi（纽约大学阿布扎比分校）
机构由 AI 辅助整理，请以论文原文为准。
