通过对话与知识的双向协同，提升推荐系统准确性。
ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
- 双向增强：用生成辅助检索，用检索优化生成。
- 在多个基准上达到最佳推荐准确率。
- 无需额外标注，适合持续更新的知识密集型场景。
将对话与外部领域知识结合对对话式推荐系统（CRS）理解用户偏好至关重要。现有方法或需领域特异性工程以限制灵活性，或依赖大语言模型而增加幻觉风险。尽管检索增强生成（RAG）有潜力，但其在CRS中的直接应用受限于噪声对话削弱检索效果，以及相似物品间细微差异被忽略。我们提出ReGeS，一种双向检索-生成协同框架，通过生成增强检索以提炼对话中的用户意图，并利用检索增强生成来区分物品间的细微特征。该协同机制无需额外标注，减少幻觉，简化持续更新。在多个CRS基准上的实验表明，ReGeS在推荐准确率上达到当前最优性能，验证了双向协同在知识密集型任务中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。