PP-DocBee2: Improved Baselines with Efficient Data for Multimodal Document Understanding

• URL: http://arxiv.org/abs/2506.18023v2
• Date: Wed, 25 Jun 2025 02:40:39 GMT
• Title: PP-DocBee2: Improved Baselines with Efficient Data for Multimodal Document Understanding
• Authors: Kui Huang, Xinrong Chen, Wenyu Lv, Jincheng Liao, Guanzhong Wang, Yi Liu,
• Abstract summary: PP-DocBee2 is an advanced version of the PP-DocBee, designed to enhance multimodal document understanding.<n>Built on a large multimodal model architecture, PP-DocBee2 addresses the limitations of its predecessor through key technological improvements.<n>These enhancements yield an $11.4%$ performance boost on internal benchmarks for Chinese business documents, and reduce inference latency by $73.0%$ to the vanilla version.
• Score: 2.778335169230448
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This report introduces PP-DocBee2, an advanced version of the PP-DocBee, designed to enhance multimodal document understanding. Built on a large multimodal model architecture, PP-DocBee2 addresses the limitations of its predecessor through key technological improvements, including enhanced synthetic data quality, improved visual feature fusion strategy, and optimized inference methodologies. These enhancements yield an $11.4\%$ performance boost on internal benchmarks for Chinese business documents, and reduce inference latency by $73.0\%$ to the vanilla version. A key innovation of our work is a data quality optimization strategy for multimodal document tasks. By employing a large-scale multimodal pre-trained model to evaluate data, we apply a novel statistical criterion to filter outliers, ensuring high-quality training data. Inspired by insights into underutilized intermediate features in multimodal models, we enhance the ViT representational capacity by decomposing it into layers and applying a novel feature fusion strategy to improve complex reasoning. The source code and pre-trained model are available at \href{https://github.com/PaddlePaddle/PaddleMIX}{https://github.com/PaddlePaddle/PaddleMIX}.

Related papers

• PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks [10.214889337096773]
  PP-DocBee is a novel multimodal large language model designed for end-to-end document image understanding.<n>We develop a data synthesis strategy tailored to document scenarios in which we build a diverse dataset to improve the model generalization.<n>We apply a few training techniques, including dynamic proportional sampling, data preprocessing, and OCR postprocessing strategies.
  arXiv  Detail & Related papers  (2025-03-06T03:43:21Z)
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling [128.24325909395188]
  We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0.<n>InternVL 2.5 exhibits competitive performance, rivaling leading commercial models such as GPT-4o and Claude-3.5-Sonnet.<n>We hope this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems.
  arXiv  Detail & Related papers  (2024-12-06T18:57:08Z)
• Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines [63.22096609916707]
  Multi-modal Retrieval Augmented Multi-modal Generation (M$2$RAG) is a novel task that enables foundation models to process multi-modal web content.<n>Despite its potential impact, M$2$RAG remains understudied, lacking comprehensive analysis and high-quality data resources.
  arXiv  Detail & Related papers  (2024-11-25T13:20:19Z)
• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization [65.64108848398696]
  We introduce a preference optimization (PO) process to enhance the multimodal reasoning capabilities of MLLMs.<n>Specifically, we design an automated preference data construction pipeline to create MMPR, a high-quality, large-scale multimodal reasoning preference dataset.<n>We explore integrating PO with MLLMs, developing a simple yet effective method, termed Mixed Preference Optimization (MPO), which boosts multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-11-15T18:59:27Z)
• What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices [91.71951459594074]
  Long language models (LLMs) with extended context windows have significantly improved tasks such as information extraction, question answering, and complex planning scenarios.<n>Existing methods typically utilize the Self-Instruct framework to generate instruction tuning data for better long context capability improvement.<n>We propose the Multi-agent Interactive Multi-hop Generation framework, incorporating a Quality Verification Agent, a Single-hop Question Generation Agent, a Multiple Question Sampling Strategy, and a Multi-hop Question Merger Agent.<n>Our findings show that our synthetic high-quality long-context instruction data significantly enhances model performance, even surpassing models trained on larger amounts of human
  arXiv  Detail & Related papers  (2024-09-03T13:30:00Z)
• Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development [67.55944651679864]
  We present a new sandbox suite tailored for integrated data-model co-development.<n>This sandbox provides a feedback-driven experimental platform, enabling cost-effective and guided refinement of both data and models.
  arXiv  Detail & Related papers  (2024-07-16T14:40:07Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization [11.02198476454955]
  We propose fine-tuning an MDS baseline with a reward that balances a reference-based metric with coverage of the input documents. Experimental results over the Multi-News and WCEP MDS datasets show significant improvements of up to +0.95 pp average ROUGE score and +3.17 pp METEOR score over the baseline.
  arXiv  Detail & Related papers  (2022-03-06T07:33:01Z)

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.