ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Dayu, Fang, Hui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912605966172160
author Yang, Dayu
Fang, Hui
author_facet Yang, Dayu
Fang, Hui
contents Connecting conversation with external domain knowledge is vital for conversational recommender systems (CRS) to correctly understand user preferences. However, existing solutions either require domain-specific engineering, which limits flexibility, or rely solely on large language models, which increases the risk of hallucination. While Retrieval-Augmented Generation (RAG) holds promise, its naive use in CRS is hindered by noisy dialogues that weaken retrieval and by overlooked nuances among similar items. We propose ReGeS, a reciprocal Retrieval-Generation Synergy framework that unifies generation-augmented retrieval to distill informative user intent from conversations and retrieval-augmented generation to differentiate subtle item features. This synergy obviates the need for extra annotations, reduces hallucinations, and simplifies continuous updates. Experiments on multiple CRS benchmarks show that ReGeS achieves state-of-the-art performance in recommendation accuracy, demonstrating the effectiveness of reciprocal synergy for knowledge-intensive CRS tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21371
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
Yang, Dayu
Fang, Hui
Information Retrieval
Artificial Intelligence
Computation and Language
Machine Learning
Connecting conversation with external domain knowledge is vital for conversational recommender systems (CRS) to correctly understand user preferences. However, existing solutions either require domain-specific engineering, which limits flexibility, or rely solely on large language models, which increases the risk of hallucination. While Retrieval-Augmented Generation (RAG) holds promise, its naive use in CRS is hindered by noisy dialogues that weaken retrieval and by overlooked nuances among similar items. We propose ReGeS, a reciprocal Retrieval-Generation Synergy framework that unifies generation-augmented retrieval to distill informative user intent from conversations and retrieval-augmented generation to differentiate subtle item features. This synergy obviates the need for extra annotations, reduces hallucinations, and simplifies continuous updates. Experiments on multiple CRS benchmarks show that ReGeS achieves state-of-the-art performance in recommendation accuracy, demonstrating the effectiveness of reciprocal synergy for knowledge-intensive CRS tasks.
title ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
topic Information Retrieval
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2509.21371