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

• URL: http://arxiv.org/abs/2511.15141v1
• Date: Wed, 19 Nov 2025 05:39:14 GMT
• Title: ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation
• Abstract summary: To better adapt large language models for recommendation, retrieval-augmented generation (RAG) has been incorporated.<n>We propose ItemRAG, an item-based RAG method for LLM-based recommendation that retrieves relevant items (rather than users) from item-item co-purchase histories.<n>We show that ItemRAG consistently improves the zero-shot LLM-based recommender by up to 43% in Hit-Ratio-1 and (2) outperforms user-based RAG baselines under both standard and cold-start item recommendation settings.
• Score: 45.55656427302983
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recently, large language models (LLMs) have been widely used as recommender systems, owing to their strong reasoning capability and their effectiveness in handling cold-start items. To better adapt LLMs for recommendation, retrieval-augmented generation (RAG) has been incorporated. Most existing RAG methods are user-based, retrieving purchase patterns of users similar to the target user and providing them to the LLM. In this work, we propose ItemRAG, an item-based RAG method for LLM-based recommendation that retrieves relevant items (rather than users) from item-item co-purchase histories. ItemRAG helps LLMs capture co-purchase patterns among items, which are beneficial for recommendations. Especially, our retrieval strategy incorporates semantically similar items to better handle cold-start items and uses co-purchase frequencies to improve the relevance of the retrieved items. Through extensive experiments, we demonstrate that ItemRAG consistently (1) improves the zero-shot LLM-based recommender by up to 43% in Hit-Ratio-1 and (2) outperforms user-based RAG baselines under both standard and cold-start item recommendation settings.

Related papers

• Training-Free LLM-Based Recommendation with Post-LLM Item Refinement Using Collaborative Signals [36.81561019224549]
  CoRRe is a training-free recommendation framework with a post-LLM paradigm.<n>We propose CoRRe, a training-free recommendation framework with a post-LLM paradigm.
  arXiv  Detail & Related papers  (2026-08-20T06:01:59Z)
• AgentDR Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents [42.177723613925146]
  We propose a novel LLM-agent framework, AgenDR, which bridges LLM reasoning with scalable recommendation tools.<n>Our approach delegates full-ranking tasks to traditional models while utilizing LLMs to integrate multiple recommendation outputs.<n>We show that our framework achieves superior full-ranking performance, yielding on average a twofold improvement over its underlying tools.
  arXiv  Detail & Related papers  (2025-10-07T05:48:05Z)
• DeepRec: Towards a Deep Dive Into the Item Space with Large Language Model Based Recommendation [83.21140655248624]
  Large language models (LLMs) have been introduced into recommender systems (RSs)<n>We propose DeepRec, a novel LLM-based RS that enables autonomous multi-turn interactions between LLMs and TRMs for deep exploration of the item space.<n> Experiments on public datasets demonstrate that DeepRec significantly outperforms both traditional and LLM-based baselines.
  arXiv  Detail & Related papers  (2025-05-22T15:49:38Z)
• Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems [65.75265303064654]
  Conversational recommender systems (CRS) aim to provide personalized recommendations via interactive dialogues with users.<n>Large language models (LLMs) enhance CRS with their superior understanding of context-aware user preferences.<n>We propose CRAG, Collaborative Retrieval Augmented Generation for LLM-based CRS.
  arXiv  Detail & Related papers  (2025-02-19T22:47:40Z)
• LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing [70.35888047551643]
  We present LaRA, a novel benchmark specifically designed to rigorously compare RAG and LC LLMs.<n>LaRA encompasses 2326 test cases across four practical QA task categories and three types of naturally occurring long texts.<n>We find that the optimal choice between RAG and LC depends on a complex interplay of factors, including the model's parameter size, long-text capabilities, context length, task type, and the characteristics of the retrieved chunks.
  arXiv  Detail & Related papers  (2025-02-14T08:04:22Z)
• RecCocktail: A Generalizable and Efficient Framework for LLM-Based Recommendation [89.19433104622694]
  We propose a generalizable and efficient LLM-based recommendation framework RecCocktail.<n>Our approach begins with fine-tuning a "base spirit" LoRA module using domain-general recommendation instruction data.<n>We then provide an entropy-guided adaptive merging method to mix the "base spirit" and the "ingredient" in the weight space.
  arXiv  Detail & Related papers  (2025-02-12T10:24:22Z)
• Beyond Retrieval: Generating Narratives in Conversational Recommender Systems [4.73461454584274]
  We introduce a new dataset (REGEN) for natural language generation tasks in conversational recommendations.<n>We establish benchmarks using well-known generative metrics, and perform an automated evaluation of the new dataset using a rater LLM.<n>And to the best of our knowledge, represents the first attempt to analyze the capabilities of LLMs in understanding recommender signals and generating rich narratives.
  arXiv  Detail & Related papers  (2024-10-22T07:53:41Z)
• LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation [57.49045064294086]
  Large Language Model (LLM) has the ability to capture semantic relationships between items, independent of their popularity.<n>We introduce LLMEmb, a novel method leveraging LLM to generate item embeddings that enhance Sequential Recommender Systems (SRS) performance.
  arXiv  Detail & Related papers  (2024-09-30T03:59:06Z)
• Taxonomy-Guided Zero-Shot Recommendations with LLMs [45.81618062939684]
  Large language models (LLMs) have shown promise in recommender systems (RecSys)<n>We propose a novel method using a taxonomy dictionary to improve the clarity and structure of item information.<n>TaxRec significantly enhances recommendation quality compared to traditional zero-shot approaches.
  arXiv  Detail & Related papers  (2024-06-20T07:06:58Z)
• Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation [50.19602159938368]
  Large language models (LLMs) are revolutionizing conversational recommender systems. We propose a Reindex-Then-Adapt (RTA) framework, which converts multi-token item titles into single tokens within LLMs. Our framework demonstrates improved accuracy metrics across three different conversational recommendation datasets.
  arXiv  Detail & Related papers  (2024-05-20T15:37:55Z)
• Zero-Shot Next-Item Recommendation using Large Pretrained Language Models [16.14557830316297]
  We propose a prompting strategy called Zero-Shot Next-Item Recommendation (NIR) prompting that directs LLMs to make next-item recommendations. Our strategy incorporates a 3-step prompting that guides GPT-3 to carry subtasks that capture the user's preferences. We evaluate the proposed approach using GPT-3 on MovieLens 100K dataset and show that it achieves strong zero-shot performance.
  arXiv  Detail & Related papers  (2023-04-06T15:35:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.