有界人设在分类任务上匹配检索，但在回归任务上不及

AI 摘要

本文提出 PersonaLink，一种无需训练的方法，将用户历史蒸馏为有界的三字段人设，并通过递归自评优化。在 LaMP-2 新闻分类任务上，其准确率与 BM25 检索相当；但在 LaMP-3 产品评分回归任务上，检索显著更强。研究发现，蒸馏人设仅在分类任务上可替代检索，且递归优化在第一轮后趋于饱和。

正文节选

Bounded Personas Match Retrieval on Classification but Not Regression for a Frozen Agent Abstract A personalized language agent must convert a user’s interaction history into behavior on each new request at inference time. Two strategies dominate. Retrieval pulls a few of the user’s most relevant past items into the prompt, which is accurate but pays a per-query selection and context cost that grows with the history. Distillation instead compresses the history once into a compact natural-languag

发布时间：2026-09-04 12:00

抓取时间：2026-09-04 12:02

来源机构：arXiv