用推理生成用户可能行为，增强冷启动用户的个性化文本生成
Reasoning-Based Personalized Generation for Users with Sparse Data
- 通过预测用户未来可能交互的内容，补全稀疏的用户历史
- 结合推理生成的虚拟互动数据，显著提升个性化生成效果
- 适合冷启动用户、新注册用户等缺乏历史数据的场景
大语言模型（LLM）个性化生成在利用用户上下文和历史方面潜力巨大。然而，现实中的用户通常交互历史稀疏，个人上下文有限，如社交平台的新用户或电商平台的新客户，这削弱了基于LLM的个性化生成能力。为此，我们提出GraSPer（基于图的稀疏个性化推理）框架，用于在稀疏上下文下增强个性化文本生成。GraSPer首先通过预测用户未来可能交互的项目来扩充用户上下文；随后通过推理对齐，为这些预测交互生成文本以丰富上下文；最终，基于真实与合成的历史生成个性化输出，确保与用户风格和偏好一致。在三个基准个性化生成数据集上的大量实验表明，GraSPer实现了显著性能提升，大幅改善了稀疏用户上下文下的个性化表现。
原文摘要 · Abstract (English)
Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, real-world users usually possess sparse interaction histories with limited personal context, such as cold-start users in social platforms and newly registered customers in online E-commerce platforms, compromising the LLM-based personalized generation. To address this challenge, we introduce GraSPer (Graph-based Sparse Personalized Reasoning), a novel framework for enhancing personalized text generation under sparse context. GraSPer first augments user context by predicting items that the user would likely interact with in the future. With reasoning alignment, it then generates texts for these interactions to enrich the augmented context. In the end, it generates personalized outputs conditioned on both the real and synthetic histories, ensuring alignment with user style and preferences. Extensive experiments on three benchmark personalized generation datasets show that GraSPer achieves significant performance gain, substantially improving personalization in sparse user context settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。