mlsanityData to 7 Oct 2026

DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue

arXiv 2502.13847 ↗First posted 19 Feb 2025cs.CL cs.AI cs.LGcited by 10

On the map: Retrieval-augmented generation → Conversational and speech RAG

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems have shown substantial benefits in applications such as question answering and multi-turn dialogue citeplewis2020retrieval. 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 citepstafford1987conversational. 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.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation. Builds on 20 of its 42 references that are in the map. First posted on arXiv 19 Feb 2025.

Builds on

20 of 42 references.

References · 20

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  9. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  10. 2018CoQA: A Conversational Question Answering Challengecited by 674
  11. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 443
  12. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266
8 more
  1. 2022Selective Annotation Makes Language Models Better Few-Shot Learnerscited by 242
  2. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  3. 2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answeringcited by 95
  4. 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 89
  5. 2024Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrieverscited by 83
  6. 2021Few-Shot Conversational Dense Retrievalcited by 71
  7. 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
  8. 2018Memory-augmented Dialogue Management for Task-oriented Dialogue Systemscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 6.

10 papers.

  1. 2026BMAM: Brain-inspired Multi-Agent Memory Frameworkcited by 3
  2. 2025Memorization and Knowledge Injection in Gated LLMscited by 2
  3. 2025Large Language Models for Oral History Understanding with Text Classification and Sentiment Analysiscited by 2
  4. 2025Implementing Long Text Style Transfer with LLMs through Dual-Layered Sentence and Paragraph Structure Extraction and Mappingcited by 1
  5. 2025From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascadescited by 1
  6. 2026Context-Agent: Dynamic Discourse Trees for Non-Linear Dialoguecited by 1
  7. 2026Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QAcited by 0
  8. 2026UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilitiescited by 0
  9. 2026Improving Multi-turn Dialogue Consistency with Self-Recall Thinkingcited by 0
  10. 2026An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestrationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation
  2. 2024Toward Conversational Agents with Context and Time Sensitive Long-term Memory
  3. 2024RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
  4. 2025MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems
  5. 2024Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA
  6. 2026CMT-RAG: Complementary Memory Traces for Multi-turn Multi-hop RAG
  7. 2024UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems
  8. 2024RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues