# Conversational and speech RAG

Area: [Retrieval-augmented generation](https://mlsanity.com/rag/index.md). HTML: https://mlsanity.com/rag/conversational-and-speech-rag/

## Key facts

- Conversational and speech RAG: 73 papers on arXiv since 2021 (data through 14 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 papers 17 Sep–14 Oct.

## Most cited here

- [MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2501.03468/) (2025), cited by 8 papers here
- [RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues](https://mlsanity.com/paper/2409.12558/) (2024), cited by 7 papers here
- [Retrieval-Augmented Text-to-Audio Generation](https://mlsanity.com/paper/2309.08051/) (2023), cited by 4 papers here
- [Retrieval Augmented End-to-End Spoken Dialog Models](https://mlsanity.com/paper/2402.01828/) (2024), cited by 3 papers here
- [UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems](https://mlsanity.com/paper/2401.13256/) (2024), cited by 2 papers here
- [IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues](https://mlsanity.com/paper/2405.13021/) (2024), cited by 2 papers here
- [CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation](https://mlsanity.com/paper/2410.23090/) (2024), cited by 2 papers here
- [Speech Retrieval-Augmented Generation without Automatic Speech Recognition](https://mlsanity.com/paper/2412.16500/) (2024), cited by 2 papers here
- [SEAL: Speech Embedding Alignment Learning for Speech Large Language Model with Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.02603/) (2025), cited by 2 papers here
- [MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations](https://mlsanity.com/paper/2602.23184/) (2026), cited by 2 papers here

## New (17 Sep–14 Oct)

- [Lost in Conversation or Lost in Translation? Diagnosing Multi-Turn Degradation in RAG](https://mlsanity.com/paper/2609.36700/) (2026-09-29)