# Graph Retrieval-Augmented LLM for Conversational Recommendation Systems

arXiv: https://arxiv.org/abs/2503.06430 · HTML: https://mlsanity.com/paper/2503.06430/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation.
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Placed in

- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [A Survey on Conversational Recommender Systems](https://mlsanity.com/paper/2004.00646/) (2020)
- [Large Language Models as Zero-Shot Conversational Recommenders](https://mlsanity.com/paper/2308.10053/) (2023)
- [Improving Conversational Recommender Systems via Knowledge Graph based Semantic Fusion](https://mlsanity.com/paper/2007.04032/) (2020)
- [Towards Knowledge-Based Recommender Dialog System](https://mlsanity.com/paper/1908.05391/) (2019)
- [INSPIRED: Toward Sociable Recommendation Dialog Systems](https://mlsanity.com/paper/2009.14306/) (2020)
- [Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning](https://mlsanity.com/paper/2206.09363/) (2022)
- [Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models](https://mlsanity.com/paper/2410.13080/) (2024)
- [CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation](https://mlsanity.com/paper/2403.06447/) (2024)
- [CRSLab: An Open-Source Toolkit for Building Conversational Recommender System](https://mlsanity.com/paper/2101.00939/) (2021)
- [Large Language Models Enhanced Collaborative Filtering](https://mlsanity.com/paper/2403.17688/) (2024)
- [BARCOR: Towards A Unified Framework for Conversational Recommendation Systems](https://mlsanity.com/paper/2203.14257/) (2022)
- [Parameter-Efficient Conversational Recommender System as a Language Processing Task](https://mlsanity.com/paper/2401.14194/) (2024)
- [Knowledge Graphs and Pre-trained Language Models enhanced Representation Learning for Conversational Recommender Systems](https://mlsanity.com/paper/2312.10967/) (2023)
- [COLA: Improving Conversational Recommender Systems by Collaborative Augmentation](https://mlsanity.com/paper/2212.07767/) (2022)
- [Reasoning over User Preferences: Knowledge Graph-Augmented LLMs for Explainable Conversational Recommendations](https://mlsanity.com/paper/2411.14459/) (2024)

## Built on by (most cited first, 10 of 10)

- [Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?](https://mlsanity.com/paper/2510.16582/) (2025)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation](https://mlsanity.com/paper/2506.20817/) (2025)
- [ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation](https://mlsanity.com/paper/2511.15141/) (2025)
- [Mixture-of-Experts Knowledge Graph Retrieval-Augmented Generation for Multi-Agent LLM-based Recommendation](https://mlsanity.com/paper/2605.28175/) (2026)
- [MATRAG: Multi-Agent Transparent Retrieval-Augmented Generation for Explainable Recommendations](https://mlsanity.com/paper/2604.20848/) (2026)
- [LumiCRS: Asymmetric Contrastive Prototype Learning for Long-Tail Conversational Recommender Systems](https://mlsanity.com/paper/2507.04722/) (2025)
- [Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation](https://mlsanity.com/paper/2605.07613/) (2026)
- [Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation](https://mlsanity.com/paper/2609.08599/) (2026)
- [AgentWebRec: Compact Evidence Fusion over the Agent Web for Personalized Recommendation](https://mlsanity.com/paper/2610.01705/) (2026)

## Abstract (arXiv)

Conversational Recommender Systems (CRSs) have emerged as a transformative paradigm for offering personalized recommendations through natural language dialogue. However, they face challenges with knowledge sparsity, as users often provide brief, incomplete preference statements. While recent methods have integrated external knowledge sources to mitigate this, they still struggle with semantic understanding and complex preference reasoning. Recent Large Language Models (LLMs) demonstrate promising capabilities in natural language understanding and reasoning, showing significant potential for CRSs. Nevertheless, due to the lack of domain knowledge, existing LLM-based CRSs either produce hallucinated recommendations or demand expensive domain-specific training, which largely limits their applicability. In this work, we present G-CRS (Graph Retrieval-Augmented Large Language Model for Conversational Recommender Systems), a novel training-free framework that combines graph retrieval-augmented generation and in-context learning to enhance LLMs' recommendation capabilities. Specifically, G-CRS employs a two-stage retrieve-and-recommend architecture, where a GNN-based graph reasoner first identifies candidate items, followed by Personalized PageRank exploration to jointly discover potential items and similar user interactions. These retrieved contexts are then transformed into structured prompts for LLM reasoning, enabling contextually grounded recommendations without task-specific training. Extensive experiments on two public datasets show that G-CRS achieves superior recommendation performance compared to existing methods without requiring task-specific training.