# TextlessRAG: End-to-End Visual Document RAG by Speech Without Text

arXiv: https://arxiv.org/abs/2509.07538 · HTML: https://mlsanity.com/paper/2509.07538/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 20 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 17 of 17)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [InfographicVQA](https://mlsanity.com/paper/2104.12756/) (2021)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [Unifying Multimodal Retrieval via Document Screenshot Embedding](https://mlsanity.com/paper/2406.11251/) (2024)
- [ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents](https://mlsanity.com/paper/2502.18017/) (2025)
- [VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents](https://mlsanity.com/paper/2504.09795/) (2025)
- [Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review](https://mlsanity.com/paper/2502.16586/) (2025)
- [Spoken question answering for visual queries](https://mlsanity.com/paper/2505.23308/) (2025)

## Built on by (most cited first, 2 of 2)

- [Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval](https://mlsanity.com/paper/2602.19961/) (2026)
- [Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey](https://mlsanity.com/paper/2601.03262/) (2025)

## Abstract (arXiv)

Document images encapsulate a wealth of knowledge, while the portability of spoken queries enables broader and flexible application scenarios. Yet, no prior work has explored knowledge base question answering over visual document images with queries provided directly in speech. We propose TextlessRAG, the first end-to-end framework for speech-based question answering over large-scale document images. Unlike prior methods, TextlessRAG eliminates ASR, TTS and OCR, directly interpreting speech, retrieving relevant visual knowledge, and generating answers in a fully textless pipeline. To further boost performance, we integrate a layout-aware reranking mechanism to refine retrieval. Experiments demonstrate substantial improvements in both efficiency and accuracy. To advance research in this direction, we also release the first bilingual speech--document RAG dataset, featuring Chinese and English voice queries paired with multimodal document content. Both the dataset and our pipeline will be made available at repository:https://github.com/xiepeijinhit-hue/textlessrag