LettinGo：探索推荐系统中的用户画像生成

LettinGo: Explore User Profile Generation for Recommendation System

June 23, 2025

作者: Lu Wang, Di Zhang, Fangkai Yang, Pu Zhao, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Qingwei Lin, Weiwei Deng, Dongmei Zhang, Feng Sun, Qi Zhang

cs.AI

摘要

用户画像对于推荐系统至关重要，它将原始的用户交互数据转化为简洁且结构化的表示，从而驱动个性化推荐。传统的基于嵌入的画像方法缺乏可解释性和适应性，而近期大语言模型（LLMs）的进展使得基于文本的画像在语义上更为丰富且透明。然而，现有方法往往遵循固定格式，限制了其捕捉用户行为多样性的能力。本文提出LettinGo，一种生成多样化且自适应用户画像的新框架。通过利用LLMs的表达能力并结合下游推荐任务的直接反馈，我们的方法避免了监督微调（SFT）带来的严格限制。相反，我们采用直接偏好优化（DPO）来使画像生成器与任务特定性能对齐，确保画像保持适应性和有效性。LettinGo分三个阶段运行：（1）通过多个LLMs探索多样化的用户画像，（2）基于其在推荐系统中的影响评估画像质量，（3）利用任务性能衍生的成对偏好数据对齐画像生成。实验结果表明，我们的框架显著提升了推荐准确性、灵活性和上下文感知能力。这项工作将画像生成作为下一代推荐系统的关键创新加以推进。

English

User profiling is pivotal for recommendation systems, as it transforms raw user interaction data into concise and structured representations that drive personalized recommendations. While traditional embedding-based profiles lack interpretability and adaptability, recent advances with large language models (LLMs) enable text-based profiles that are semantically richer and more transparent. However, existing methods often adhere to fixed formats that limit their ability to capture the full diversity of user behaviors. In this paper, we introduce LettinGo, a novel framework for generating diverse and adaptive user profiles. By leveraging the expressive power of LLMs and incorporating direct feedback from downstream recommendation tasks, our approach avoids the rigid constraints imposed by supervised fine-tuning (SFT). Instead, we employ Direct Preference Optimization (DPO) to align the profile generator with task-specific performance, ensuring that the profiles remain adaptive and effective. LettinGo operates in three stages: (1) exploring diverse user profiles via multiple LLMs, (2) evaluating profile quality based on their impact in recommendation systems, and (3) aligning the profile generation through pairwise preference data derived from task performance. Experimental results demonstrate that our framework significantly enhances recommendation accuracy, flexibility, and contextual awareness. This work enhances profile generation as a key innovation for next-generation recommendation systems.