paper-with-me

홈 › Papers

Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning

2024-02-26 · Jinxu Zhang

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly, ignoring the source document's evidence and lacking interpretability. In this work, we address the lack of step-wise capabilities through data augmentation and extension. Specifically, We use Multi-modal Large Language Models (MLLMs), which have strong visual understanding and reasoning abilities, as data generators to generate step-wise question-and-answer pairs for document images and use a high-performance LLM as the error detector to filter out noisy data. This step-wise data generation pipeline is implemented using both template-based and few-shot methods. We then use the generated high-quality data to train a humanized document understanding and reasoning model, specifically designed to solve complex questions that require reasoning or multi-hop question answering, dubbed DocAssistant. Experimental results demonstrate the effectiveness and application value of step-wise generation, showing a 5 improvement on InfoVQA with complex layouts and a 7 improvement on ChartQA with complex reasoning, compared to directly generated answers. We hope our work highlights the potential of synthetic data and encourages further exploration of multi-modal document reasoning capabilities.

📄 PDF Abstract BibTeX arXiv:2403.00816

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentationdocument understandingLanguage ModelingLanguage ModellingLarge Language ModelMulti-hop Question AnsweringQuestion AnsweringRetrievalVisual Question Answering

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

AtomThink: A Slow Thinking Framework for Multimodal Mathematical Reasoning

2024-11-18 · Kun Xiang, Zhili Liu, Zihao Jiang, Yunshuang Nie 외

In this paper, we address the challenging task of multimodal mathematical reasoning by incorporating the ability of ``slow thinking" into multimodal large language models (MLLMs). Contrary to existing methods that rely o…

Mathematical Reasoning

ImageNet-Think-250K: A Large-Scale Synthetic Dataset for Multimodal Reasoning for Vision Language Models

2025-10-02 · Krishna Teja Chitty-Venkata, Murali Emani arxiv

We develop ImageNet-Think, a multimodal reasoning dataset designed to aid the development of Vision Language Models (VLMs) with explicit reasoning capabilities. Our dataset is built on 250,000 images from ImageNet21k dat…

Multimodal Reasoning

OneThinker: All-in-one Reasoning Model for Image and Video

2025-12-02 · Kaituo Feng, Manyuan Zhang, Hongyu Li, Kaixuan Fan 외 arxiv

Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typically train separate models for differe…

Zero-shot GeneralizationReinforcement LearningMultimodal ReasoningQuestion Answering

ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing

2025-06-26 · Huadai Liu, Jialei Wang, Kaicheng Luo, Wen Wang 외

While end-to-end video-to-audio generation has greatly improved, producing high-fidelity audio that authentically captures the nuances of visual content remains challenging. Like professionals in the creative industries,…

Audio GenerationLarge Language ModelMultimodal Large Language Model

ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks

2025-05-29 · Akashah Shabbir, Muhammad Akhtar Munir, Akshay Dudhane, Muhammad Umer Sheikh 외

Recent progress in large language models (LLMs) has enabled tool-augmented agents capable of solving complex real-world tasks through step-by-step reasoning. However, existing evaluations often focus on general-purpose o…

Spatial Reasoning