Graph Retrieval-Augmented LLM for Conversational Recommendation Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913725699588096 |
|---|---|
| author | Qiu, Zhangchi Luo, Linhao Zhao, Zicheng Pan, Shirui Liew, Alan Wee-Chung |
| author_facet | Qiu, Zhangchi Luo, Linhao Zhao, Zicheng Pan, Shirui Liew, Alan Wee-Chung |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06430 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph Retrieval-Augmented LLM for Conversational Recommendation Systems Qiu, Zhangchi Luo, Linhao Zhao, Zicheng Pan, Shirui Liew, Alan Wee-Chung Computation and Language Artificial Intelligence Information Retrieval 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. |
| title | Graph Retrieval-Augmented LLM for Conversational Recommendation Systems |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2503.06430 |