ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation

2025/11/19 by Kim, Sunwoo, Lee, Geon, Kim, Kyungho +2
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Recommender Systems and Techniques #Sentiment Analysis and Opinion Mining #Topic Modeling

paper · doi:10.48550/arxiv.2511.15141

openalex publication_date 2025/11/19 · openalex created_date 2025/11/23 · openalex updated_date 2026/07/28

Abstract

Recently, large language models (LLMs) have been widely used as recommender systems, owing to their reasoning capability and effectiveness in handling cold-start items. A common approach prompts an LLM with a target user's purchase history to recommend items from a candidate set, often enhanced with retrieval-augmented generation (RAG). Most existing RAG approaches retrieve purchase histories of users similar to the target user; however, these histories often contain noisy or weakly relevant information and provide little or no useful information for candidate items. To address these limitations, we propose ItemRAG, a novel RAG approach that shifts focus from coarse user-history retrieval to fine-grained item-level retrieval. ItemRAG augments the description of each item in the target user's history or the candidate set by retrieving items relevant to each. To retrieve items not merely semantically similar but informative for recommendation, ItemRAG leverages co-purchase information alongside semantic information. Especially, through their careful combination, ItemRAG prioritizes more informative retrievals and also benefits cold-start items. Through extensive experiments, we demonstrate that ItemRAG consistently outperforms existing RAG approaches under both standard and cold-start item recommendation settings. Supplementary materials, code, and datasets are provided at https://github.com/kswoo97/ItemRAG.

Citations

• Revisiting Prompt Engineering: A Comprehensive Evaluation for LLM-based Personalized Recommendation
• KERAG_R: Knowledge-Enhanced Retrieval-Augmented Generation for Recommendation
• Multi-Behavior Recommender Systems: A Survey
• Process-Supervised LLM Recommenders via Flow-guided Tuning
• Graph Retrieval-Augmented LLM for Conversational Recommendation Systems
• Multi-Grained Patch Training for Efficient LLM-based Recommendation
• Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation
• Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System
• The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation
• CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation
• Bridging Language and Items for Retrieval and Recommendation
• A Survey on Large Language Models for Recommendation
• Dense Passage Retrieval for Open-Domain Question Answering
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
• Self-Attentive Sequential Recommendation

Related

• PALR: Personalization Aware LLMs for Recommendation
• Large Language Models as Data Augmenters for Cold-Start Item Recommendation
• Do LLMs Understand Collaborative Signals? Diagnosis and Repair
• Selecting User Histories to Generate LLM Users for Cold-Start Item Recommendation
• RAGSys: Item-Cold-Start Recommender as RAG System