LettinGo：探索推薦系統中的用戶畫像生成

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

用戶畫像對於推薦系統至關重要，它能將原始用戶互動數據轉化為簡潔且結構化的表示，從而驅動個性化推薦。傳統基於嵌入的畫像缺乏可解釋性和適應性，而近期大型語言模型（LLMs）的進展使得基於文本的畫像在語義上更為豐富且透明。然而，現有方法往往遵循固定格式，限制了其捕捉用戶行為多樣性的能力。本文介紹了LettinGo，一個生成多樣化且自適應用戶畫像的新框架。通過利用LLMs的表達能力並整合下游推薦任務的直接反饋，我們的方法避免了監督微調（SFT）所帶來的僵化限制。相反，我們採用直接偏好優化（DPO）來使畫像生成器與任務特定性能對齊，確保畫像保持自適應性和有效性。LettinGo分三個階段運作：(1) 通過多個LLMs探索多樣化的用戶畫像，(2) 基於畫像在推薦系統中的影響評估其質量，(3) 利用從任務表現中獲得的成對偏好數據來對齊畫像生成。實驗結果表明，我們的框架顯著提升了推薦的準確性、靈活性和上下文感知能力。這項工作將畫像生成作為下一代推薦系統的關鍵創新加以推進。

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.