DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
- URL: http://arxiv.org/abs/2502.13847v1
- Date: Wed, 19 Feb 2025 16:10:43 GMT
- Title: DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
- Authors: Feiyuan Zhang, Dezhi Zhu, James Ming, Yilun Jin, Di Chai, Liu Yang, Han Tian, Zhaoxin Fan, Kai Chen,
- Abstract summary: 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.
- Score: 20.107134675821985
- License:
- Abstract: 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.
Related papers
- CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation [68.81271028921647]
We introduce CORAL, a benchmark designed to assess RAG systems in realistic multi-turn conversational settings.
CORAL includes diverse information-seeking conversations automatically derived from Wikipedia.
It supports three core tasks of conversational RAG: passage retrieval, response generation, and citation labeling.
arXiv Detail & Related papers (2024-10-30T15:06:32Z) - History-Aware Conversational Dense Retrieval [31.203399110612388]
We propose a History-Aware Conversational Dense Retrieval (HAConvDR) system, which incorporates two ideas: context-denoised query reformulation and automatic mining of supervision signals.
Experiments on two public conversational search datasets demonstrate the improved history modeling capability of HAConvDR.
arXiv Detail & Related papers (2024-01-30T01:24:18Z) - History Semantic Graph Enhanced Conversational KBQA with Temporal
Information Modeling [28.27368343751272]
We propose a History Semantic Graph Enhanced KBQA model (HSGE) that is able to effectively model long-range semantic dependencies in conversation history.
We evaluate HSGE on a widely used benchmark dataset for complex sequential question answering.
arXiv Detail & Related papers (2023-06-12T05:10:58Z) - Multi-grained Hypergraph Interest Modeling for Conversational
Recommendation [75.65483522949857]
We propose a novel multi-grained hypergraph interest modeling approach to capture user interest beneath intricate historical data.
In our approach, we first employ the hypergraph structure to model users' historical dialogue sessions and form a session-based hypergraph, which captures coarse-grained, session-level relations.
We further conduct multi-grained hypergraph convolution on the two kinds of hypergraphs, and utilize the enhanced representations to develop interest-aware CRS.
arXiv Detail & Related papers (2023-05-04T13:13:44Z) - FCC: Fusing Conversation History and Candidate Provenance for Contextual
Response Ranking in Dialogue Systems [53.89014188309486]
We present a flexible neural framework that can integrate contextual information from multiple channels.
We evaluate our model on the MSDialog dataset widely used for evaluating conversational response ranking tasks.
arXiv Detail & Related papers (2023-03-31T23:58:28Z) - History-Aware Hierarchical Transformer for Multi-session Open-domain
Dialogue System [59.78425104243993]
We propose History-Aware Hierarchical Transformer (HAHT) for multi-session open-domain dialogue.
HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context.
Experimental results on a large-scale Multi-Session Conversation dataset suggest that the proposed HAHT model consistently outperforms baseline models.
arXiv Detail & Related papers (2023-02-02T06:54:33Z) - Detecting and Classifying Malevolent Dialogue Responses: Taxonomy, Data
and Methodology [68.8836704199096]
Corpus-based conversational interfaces are able to generate more diverse and natural responses than template-based or retrieval-based agents.
With their increased generative capacity of corpusbased conversational agents comes the need to classify and filter out malevolent responses.
Previous studies on the topic of recognizing and classifying inappropriate content are mostly focused on a certain category of malevolence.
arXiv Detail & Related papers (2020-08-21T22:43:27Z) - Ranking Enhanced Dialogue Generation [77.8321855074999]
How to effectively utilize the dialogue history is a crucial problem in multi-turn dialogue generation.
Previous works usually employ various neural network architectures to model the history.
This paper proposes a Ranking Enhanced Dialogue generation framework.
arXiv Detail & Related papers (2020-08-13T01:49:56Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.