面向个性化的自监督用户画像生成
Self-supervised User Profile Generation for Personalization
AI总结：
提出BUMP框架，利用自监督双向排序目标训练大语言模型生成用户文本画像，无需下游标注即可实现个性化。
摘要：
随着大语言模型（LLM）被部署到推荐、搜索、对话和内容生成等场景——在这些场景中，相同的查询应针对不同用户给出不同答案——个性化LLM已成为核心挑战。一个有前景的方法是将每个用户的交互历史总结为自然语言记忆或画像，并将其前置到提示中以便于个性化。现有方法使用来自标注下游任务的显式奖励来学习此类画像生成器，但这种方法成本高昂且稀疏，因为需要为每个目标任务提供标注监督。鉴于这一挑战，我们引入了通过画像的双向用户建模（BUMP），这是一个自监督框架，无需任何下游标签即可训练画像生成器。具体来说，给定用户的交互历史，我们使用GRPO训练LLM在双向批次内排序目标下生成自由形式的文本画像：一个小型LLM评判器衡量（i）生成的画像作为查询时，在批次中将用户自己的保留交互排在其他用户交互之上的程度，以及（ii）一个保留交互作为查询时，在批次中将用户自己的画像排在其他用户画像之上的程度。两个方向均使用多正例NDCG评分，并合并为每次生成的密集奖励；批次中的其他用户提供免费负例，因此每个训练样本仅从原始交互日志中获得监督。在LaMP基准测试上，BUMP匹配或超越了依赖标注奖励的闭源API和先前方法，同时在训练时无需任何任务标签。
英文摘要：
Personalizing large language models (LLMs) has become a central challenge as LLMs are deployed across recommendation, search, dialogue, and content generation -- settings where the same query should yield different answers given different users. A promising route is to summarize each user's interaction history into a natural-language memory or profile and prepend it to the prompt to facilitate personalization. Existing methods learn such profile generators with explicit rewards derived from labeled downstream tasks, which are expensive and sparse as they require annotated supervision for every target task. In light of this challenge, we introduce Bidirectional User Modeling via Profiles (BUMP), a self-supervised framework that trains a profile generator without any downstream labels. Specifically, given a user's interaction history, we use GRPO to train an LLM to emit a free-form textual profile under a bidirectional in-batch ranking objective: a small LLM judge measures (i) how well the generated profile, used as a query, ranks the user's own held-out interactions above interactions from other users in the batch, and (ii) how well a held-out interaction, used as a query, ranks the user's own profile above profiles of other users. Both directions are scored with multi-positive NDCG and combined into a dense reward per rollout; other users in the batch supply free negatives, so every training example yields supervision from raw interaction logs alone. Evaluated on the LaMP benchmark, BUMP matches or outperforms closed-source APIs and prior methods relying on labeled rewards, while requiring no task label at training.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
