DUET: Joint Exploration of User Item Profiles in Recommendation System

2026-04-15

AI Summary

This work addresses the limitations of traditional recommendation systems that rely on dense vectors and existing large language model–based approaches constrained by fixed templates, which often lead to semantic inconsistency in user and item textual profiles. To overcome this, the authors propose DUET, a template-free, joint, and interaction-aware framework for textual profile generation through a three-stage pipeline: first compressing raw behavioral and metadata into concise cues, then constructing user–item paired prompts to generate coherent profiles, and finally optimizing the generation process via reinforcement learning with recommendation performance as the reward signal. This approach ensures semantic consistency while directly aligning profile generation with downstream recommendation efficacy. Extensive experiments on three real-world datasets demonstrate that DUET significantly outperforms strong baselines, validating the effectiveness of template-free, jointly aligned semantic modeling.

Technology Category

• Natural Language Processing: Generation
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Traditional recommendation systems represent users and items as dense vectors and learn to align them in a shared latent space for relevance estimation. Recent LLM-based recommenders instead leverage natural-language representations that are easier to interpret and integrate with downstream reasoning modules. This paper studies how to construct effective textual profiles for users and items, and how to align them for recommendation. A central difficulty is that the best profile format is not known a priori: manually designed templates can be brittle and misaligned with task objectives. Moreover, generating user and item profiles independently may produce descriptions that are individually plausible yet semantically inconsistent for a specific user--item pair. We propose Duet, an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence. Duet follows a three-stage procedure: it first turns raw histories and metadata into compact cues, then expands these cues into paired profile prompts and then generate profiles, and finally optimizes the generation policy with reinforcement learning using downstream recommendation performance as feedback. Experiments on three real-world datasets show that Duet consistently outperforms strong baselines, demonstrating the benefits of template-free profile exploration and joint user-item textual alignment.

Problem

• textual profiles
• user-item alignment
• recommendation system
• semantic consistency
• profile generation

Innovation

• joint profile generation
• template-free prompting
• textual alignment
• reinforcement learning
• LLM-based recommendation