ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
This work addresses the challenge of improving recommendation accuracy in conversational systems for users, though it appears incremental as it builds on existing retrieval-augmented generation methods.
The paper tackles the problem of noisy dialogues and subtle item differences in conversational recommender systems by proposing ReGeS, a reciprocal retrieval-generation synergy framework, which achieves state-of-the-art performance in recommendation accuracy on multiple benchmarks.
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.