ReGeS：面向对话式推荐系统的互惠检索-生成协同框架
ReGeS: Reciprocal Retrieval-Generation Synergy for Conversational Recommender Systems
AI总结：
针对对话式推荐系统，提出互惠检索-生成协同框架ReGeS，通过生成增强检索提炼用户意图和检索增强生成区分物品细微特征，无需额外标注，在多个基准上取得最先进推荐准确性。
摘要：
将对话与外部领域知识相连接，对于对话式推荐系统（CRS）正确理解用户偏好至关重要。然而，现有解决方案要么需要特定领域的工程化处理，这限制了灵活性，要么完全依赖大型语言模型，这增加了幻觉风险。尽管检索增强生成（RAG）前景广阔，但其在CRS中的朴素应用受到嘈杂对话的阻碍，这些对话削弱了检索效果，并且忽视了相似物品之间的细微差别。我们提出了ReGeS，一个互惠的检索-生成协同框架，该框架统一了生成增强检索以从对话中提炼信息丰富的用户意图，以及检索增强生成以区分细微的物品特征。这种协同作用无需额外标注，减少了幻觉，并简化了持续更新。在多个CRS基准上的实验表明，ReGeS在推荐准确性方面达到了最先进的性能，证明了互惠协同对于知识密集型CRS任务的有效性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
