mlsanityData to 7 Oct 2026

Conversational and speech RAG

73 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: dialogue, conversational, speech, generation, retrieval

Key facts. Conversational and speech RAG: 73 papers on arXiv since 2021 (data through 7 Oct 2026). 8 of its 73 mapped papers (11%) cite “MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems” (2025, arXiv 2501.03468). 7 of its 73 mapped papers (10%) cite “RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues” (2024, arXiv 2409.12558). 1 new paper 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

1 new since 17 Sep

  1. Lost in Conversation or Lost in Translation? Diagnosing Multi-Turn Degradation in RAG

Foundations

Most cited by papers here

  1. MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems2025cited by 8 here
  2. RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues2024cited by 7 here
  3. Retrieval-Augmented Text-to-Audio Generation2023cited by 4 here
  4. Retrieval Augmented End-to-End Spoken Dialog Models2024cited by 3 here
  5. UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems2024cited by 2 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 14 here
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 43 here
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 7 here
  4. 2023In-Context Retrieval-Augmented Language Modelscited by 5 here
  5. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 2 here
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 7 here
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 9 here
  8. 2024CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systemscited by 3 here
  9. 2025MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systemscited by 8 here
15 more it builds on, not in this chain
  1. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Textcited by 3 here
  2. 2022Retrieval-Augmented Multimodal Language Modelingcited by 2 here
  3. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 4 here
  4. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 2 here
  5. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 4 here
  6. 2023Retrieval-Augmented Text-to-Audio Generationcited by 4 here
  7. 2023RECAP: Retrieval-Augmented Audio Captioningcited by 2 here
  8. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 2 here
  9. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 2 here
  10. 2024ChatQA: Surpassing GPT-4 on Conversational QA and RAGcited by 3 here
  11. 2024Retrieval Augmented End-to-End Spoken Dialog Modelscited by 3 here
  12. 2024Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Checkcited by 7 here
  13. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 3 here
  14. 2024CRAG -- Comprehensive RAG Benchmarkcited by 3 here
  15. 2024RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialoguescited by 7 here

The 24 most cited of 128.

Browse

30 of 73, ranked 6–35

  1. 6MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations20262
  2. 7SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation20252
  3. 8IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues20242
  4. 9CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation20242
  5. 10Speech Retrieval-Augmented Generation without Automatic Speech Recognition20242
  6. 11GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems20251
  7. 12On Memory Construction and Retrieval for Personalized Conversational Agents20251
  8. 13DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue20251
  9. 14WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models20251
  10. 15Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation20251
All 30
  1. 16RAGAPHENE: A RAG Annotation Platform with Human Enhancements and Edits20251
  2. 17Retrieval-Augmented Audio Deepfake Detection20241
  3. 18Toward Conversational Agents with Context and Time Sensitive Long-term Memory20241
  4. 19LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation20241
  5. 20Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA20241
  6. 21Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation20241
  7. 22Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog20211
  8. 23Retrieval-Augmented Transformer-XL for Close-Domain Dialog Generation20211
  9. 24RAC: Retrieval-Augmented Clarification for Faithful Conversational Search20260
  10. 25RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation20260
  11. 26Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA20260
  12. 27AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations20260
  13. 28Rethinking Evaluation in Retrieval-Augmented Personalized Dialogue: A Cognitive and Linguistic Perspective20260
  14. 29User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction20260
  15. 30EverydayGPT: Confidence-Gated Routing for Efficient and Safe Hybrid GPT-RAG Conversational QA20260
  16. 31H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations20260
  17. 32MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks20260
  18. 33Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents20260
  19. 34Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction20260
  20. 35RAG-Audio: Retrieval-Augmented Generation for Faithful Brain-to-Audio Reconstruction20260