Self-supervised User Profile Generation for Personalization

• URL: http://arxiv.org/abs/2606.05336v1
• Date: Wed, 03 Jun 2026 18:25:00 GMT
• Title: Self-supervised User Profile Generation for Personalization
• Abstract summary: We introduce Bidirectional User Modeling via Profiles (BUMP), a self-language framework that trains a profile generator without any downstream labels.<n>BUMP matches or outperforms closed-source APIs and prior methods relying on labeled rewards.
• Score: 29.85412538714496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch [20.2442673472594]
  ProfiLLM operationalizes utility-aligned user profiling for production matching systems through two modules.<n>It produces reusable global knowledge, adaptive user clustering rules, and region-level supply-demand priors.<n>It achieves up to +6.14% relative AUC improvement in outcome prediction, up to +4.35% GMV gain in dispatching simulation.
  arXiv  Detail & Related papers  (2026-06-17T08:15:07Z)
• DUET: Joint Exploration of User Item Profiles in Recommendation System [64.09357667290634]
  This paper studies how to construct effective textual profiles for users and items.<n>A central difficulty is that the best profile format is not known a priori.<n>We propose Duet, an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
  arXiv  Detail & Related papers  (2026-04-15T12:37:40Z)
• Towards Realistic Personalization: Evaluating Long-Horizon Preference Following in Personalized User-LLM Interactions [50.70965714314064]
  Large Language Models (LLMs) are increasingly serving as personal assistants, where users share complex and diverse preferences over extended interactions.<n>This work proposes RealPref, a benchmark for evaluating realistic preference-following in personalized user-LLM interactions.
  arXiv  Detail & Related papers  (2026-03-04T15:42:43Z)
• Users as Annotators: LLM Preference Learning from Comparison Mode [9.005226538625474]
  We consider an alternative approach to collect pairwise preference data -- user annotation from comparison mode.<n>We develop an expectation-maximization algorithm to estimate a latent quality factor of the user.
  arXiv  Detail & Related papers  (2025-10-10T08:57:34Z)
• PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization [4.624026598342624]
  We propose PrLM, a reinforcement learning framework that trains LLMs to explicitly reason over retrieved user profiles.<n>PrLM effectively learns from user responses without requiring annotated reasoning paths.<n>Experiments on three personalized text generation datasets show that PrLM outperforms existing methods.
  arXiv  Detail & Related papers  (2025-08-10T13:37:26Z)
• Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale [53.059480071818136]
  Large Language Models (LLMs) have emerged as personalized assistants for users across a wide range of tasks.<n> PERSONAMEM features curated user profiles with over 180 simulated user-LLM interaction histories.<n>We evaluate LLM chatbots' ability to identify the most suitable response according to the current state of the user's profile.
  arXiv  Detail & Related papers  (2025-04-19T08:16:10Z)
• Aligning LLMs with Individual Preferences via Interaction [51.72200436159636]
  We train large language models (LLMs) that can ''interact to align''<n>We develop a multi-turn preference dataset containing 3K+ multi-turn conversations in tree structures.<n>For evaluation, we establish the ALOE benchmark, consisting of 100 carefully selected examples and well-designed metrics to measure the customized alignment performance during conversations.
  arXiv  Detail & Related papers  (2024-10-04T17:48:29Z)
• Prompt Tuning as User Inherent Profile Inference Machine [68.16976932088708]
  We propose UserIP-Tuning, which uses prompt-tuning to infer user profiles.<n>UserIP-Tuning outperforms state-of-the-art recommendation algorithms.<n>The presented solution has been deployed in Huawei AppGallery's Explore page since May 2025.
  arXiv  Detail & Related papers  (2024-08-13T02:25:46Z)
• Reinforced Prompt Personalization for Recommendation with Large Language Models [24.360796133889156]
  We introduce the concept of instance-wise prompting, aiming at personalizing discrete prompts for individual users.<n>To improve efficiency and quality, RPP personalizes prompts at the sentence level rather than searching in the vast vocabulary word-by-word.
  arXiv  Detail & Related papers  (2024-07-24T09:24:49Z)
• Aligning Language Models with Demonstrated Feedback [58.834937450242975]
  Demonstration ITerated Task Optimization (DITTO) directly aligns language model outputs to a user's demonstrated behaviors.<n>We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts.
  arXiv  Detail & Related papers  (2024-06-02T23:13:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.