# TextlessRAG: End-to-End Visual Document RAG by Speech Without Text Source: [TextlessRAG: End-to-End Visual Document RAG by Speech Without Text]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:36:41.717Z Authors: Peijin Xie, Shun Qian, Bingquan Liu, Dexin Wang, Lin Sun, Xiangzheng Zhang Published: 2025-09-09T09:16:25.000Z ## Abstract 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 ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()