基于协同过滤的检索增强生成用于个性化文本生成
Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation
AI总结：
本文提出CFRAG方法，将协同过滤引入个性化检索增强生成，通过对比学习获取相似用户协同信息，并利用LLM反馈微调个性化检索与重排序器，在LaMP基准上验证了其有效性。
摘要：
近年来，使大型语言模型（LLMs）生成符合个体用户偏好的内容的个性化技术引起了广泛关注。个性化检索增强生成（RAG）是一种常用的个性化方法，它从用户历史中检索相关文档以反映用户偏好并增强LLM生成。然而，现有的个性化RAG方法没有考虑到相似用户的历史也可以辅助当前用户的个性化生成，这意味着用户之间的协同信息同样有利于个性化生成。受协同过滤在推荐系统中应用的启发，我们提出了一种名为CFRAG的方法，该方法将协同过滤适配到RAG中，用于个性化文本生成。然而，这带来了两个挑战：（1）如何在缺乏显式用户相似度标签的情况下融入协同信息？（2）如何检索支持个性化LLM生成的文档？针对挑战1，我们使用对比学习训练用户嵌入，以检索相似用户并引入协同信息。针对挑战2，我们设计了个性化检索器和重排序器，从这些用户的历史中检索前k个文档。我们在检索和重排序过程中考虑用户偏好。然后，我们利用LLM的反馈对个性化检索器和重排序器进行微调，使其能够检索满足LLM个性化生成需求的文档。在语言模型个性化（LaMP）基准上的实验结果验证了CFRAG的有效性。进一步分析证实了融入协同信息的重要性。
英文摘要：
Recently, the personalization of Large Language Models (LLMs) to generate content that aligns with individual user preferences has garnered widespread attention. Personalized Retrieval-Augmented Generation (RAG), which retrieves relevant documents from the user's history to reflect their preferences and enhance LLM generation, is one commonly used approach for personalization. However, existing personalized RAG methods do not consider that the histories of similar users can also assist in personalized generation for the current user, meaning that collaborative information between users can also benefit personalized generation. Inspired by the application of collaborative filtering in recommender systems, we propose a method called CFRAG, which adapts Collaborative Filtering to RAG for personalized text generation. However, this presents two challenges: (1)~how to incorporate collaborative information without explicit user similarity labels? (2)~how to retrieve documents that support personalized LLM generation? For Challenge 1, we use contrastive learning to train user embeddings to retrieve similar users and introduce collaborative information. For Challenge 2, we design a personalized retriever and reranker to retrieve the top-$k$ documents from these users' histories. We take into account the user's preference during retrieval and reranking. Then we leverage feedback from the LLM to fine-tune the personalized retriever and reranker, enabling them to retrieve documents that meet the personalized generation needs of the LLM. Experimental results on the Language Model Personalization (LaMP) benchmark validate the effectiveness of CFRAG. Further analysis confirms the importance of incorporating collaborative information.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
