DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
This addresses the challenge of maintaining conversational context for multi-turn dialogue systems, though it appears incremental by building on existing RAG frameworks.
The paper tackles the problem of traditional RAG methods overlooking dynamic historical context in multi-turn dialogues by introducing DH-RAG, which uses a dynamic historical database and query reconstruction to improve responses, resulting in significant enhancements in relevance, coherence, and quality on benchmarks.
Retrieval-Augmented Generation (RAG) systems have shown substantial benefits in applications such as question answering and multi-turn dialogue \citep{lewis2020retrieval}. However, traditional RAG methods, while leveraging static knowledge bases, often overlook the potential of dynamic historical information in ongoing conversations. To bridge this gap, we introduce DH-RAG, a Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue. DH-RAG is inspired by human cognitive processes that utilize both long-term memory and immediate historical context in conversational responses \citep{stafford1987conversational}. DH-RAG is structured around two principal components: a History-Learning based Query Reconstruction Module, designed to generate effective queries by synthesizing current and prior interactions, and a Dynamic History Information Updating Module, which continually refreshes historical context throughout the dialogue. The center of DH-RAG is a Dynamic Historical Information database, which is further refined by three strategies within the Query Reconstruction Module: Historical Query Clustering, Hierarchical Matching, and Chain of Thought Tracking. Experimental evaluations show that DH-RAG significantly surpasses conventional models on several benchmarks, enhancing response relevance, coherence, and dialogue quality.