DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning

• URL: http://arxiv.org/abs/2604.22281v1
• Date: Fri, 24 Apr 2026 06:51:58 GMT
• Title: DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
• Abstract summary: We propose DocPrune, a training-free and progressive document token pruning framework.<n>Our experiments on the M3DocRAG show that DocPrune improves throughput by 3.0x and 3.3x in the encoder and decoder, respectively.
• Score: 41.26256203983725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in vision-language models have demonstrated remarkable performance across diverse multi-modal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike natural images, document images contain large backgrounds and only sparse supporting evidence, leading to the inefficient consumption of substantial computational resources, especially for long documents. We observe that existing token-reduction methods for natural images and videos fall short in utilizing the structural sparsity unique to documents. To address this, we propose DocPrune, a training-free and progressive document token pruning framework designed for efficient long-document understanding. The proposed method preserves only the essential tokens for the task while removing unnecessary ones, such as background or question-irrelevant tokens. Moreover, it automatically selects the appropriate layers to initiate token pruning based on the model's level of comprehension. Our experiments on the M3DocRAG show that DocPrune improves throughput by 3.0x and 3.3x in the encoder and decoder, respectively, while boosting the F1 score by +1.0, achieving both higher accuracy and efficiency without any additional training.

Related papers

• MonkeyOCRv2: A Visual-Text Foundation Model for Document AI [71.06391669976786]
  MonkeyOCRv2 is a visual-text pretrained model for document AI.<n> MonkeyDoc v2 is the largest document-image pretraining corpus, comprising 113 million images spanning 17 languages.
  arXiv  Detail & Related papers  (2026-07-13T13:43:39Z)
• MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing [74.84107522458798]
  MPDocBench-Parse is a benchmark for multi-page document parsing in real-world applications.<n>It contains 433 manually annotated documents with 3,246 pages, covering 15 document types in English and Chinese, with diverse layout styles.
  arXiv  Detail & Related papers  (2026-05-21T07:36:41Z)
• VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization [7.769156392417315]
  Key Information Extraction underpins the understanding of visual documents.<n>Existing multimodal large language models (MLLMs) often perform poorly on dense documents.<n>We introduce VDInstruct, an MLLM that separates spatial region detection from semantic feature extraction.
  arXiv  Detail & Related papers  (2025-07-13T08:15:11Z)
• mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding [103.05835688963947]
  We propose a High-resolution DocCompressor module to compress each high-resolution document image into 324 tokens. DocOwl2 sets a new state-of-the-art across multi-page document understanding benchmarks and reduces first token latency by more than 50%. Compared to single-image MLLMs trained on similar data, our DocOwl2 achieves comparable single-page understanding performance with less than 20% of the visual tokens.
  arXiv  Detail & Related papers  (2024-09-05T11:09:00Z)
• Visually Guided Generative Text-Layout Pre-training for Document Intelligence [51.09853181377696]
  We propose visually guided generative text-pre-training, named ViTLP. Given a document image, the model optimize hierarchical language and layout modeling objectives to generate the interleaved text and layout sequence. ViTLP can function as a native OCR model to localize and recognize texts of document images.
  arXiv  Detail & Related papers  (2024-03-25T08:00:43Z)
• Information Extraction from Documents: Question Answering vs Token Classification in real-world setups [0.0]
  We compare the Question Answering approach with the classical token classification approach for document key information extraction. Our research showed that when dealing with clean and relatively short entities, it is still best to use token classification-based approach.
  arXiv  Detail & Related papers  (2023-04-21T14:43:42Z)
• Unified Pretraining Framework for Document Understanding [52.224359498792836]
  We present UDoc, a new unified pretraining framework for document understanding. UDoc is designed to support most document understanding tasks, extending the Transformer to take multimodal embeddings as input. An important feature of UDoc is that it learns a generic representation by making use of three self-supervised losses.
  arXiv  Detail & Related papers  (2022-04-22T21:47:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.