paper-with-me

홈 › Papers

DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model

2025-08-18 · Qian Chen, Xianyin Zhang, Lifan Guo, Feng Chen, Chi Zhang arxiv

Recent advances in vision-language models (VLMs) have enabled end-to-end document parsing and understanding, achieving strong performance on diverse optical character recognition (OCR) tasks. However, VLMs are prone to generate words that do not exist in the input image due to over-reliance on language priors. By contrast, traditional OCR models, whose architectures are tailored for specific recognition tasks, often achieve stronger fine-grained visual perception with fewer hallucinations, but they typically lack the contextual semantic understanding and reasoning capabilities needed in more challenging cases. To bridge this gap, we propose DianJin-OCR-R1, a reasoning-enhanced framework for recognition that trains VLMs in a reasoning-and-tool interleaved paradigm. Our DianJin-OCR-R1 model first recognizes the content in the input image through its own OCR capabilities, and then calls other expert models for extra results as references. After that, it is guided to "look again" at the image and compare its own recognized content with other results to find errors or omissions. Finally, it integrates all available evidence to generate a more accurate output. This design empowers the model to learn how to implicitly re-focus on the visual input and effectively leverage the results of other expert models for better performance. We evaluate our DianJin-OCR-R1 model on ReST and OmniDocBench, where it consistently outperforms both its non-reasoning counterparts and expert models, demonstrating the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:2508.13238

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models

2025-04-22 · Jie Zhu, Qian Chen, Huaixia Dou, Junhui Li 외

Effective reasoning remains a core challenge for large language models (LLMs) in the financial domain, where tasks often require domain-specific knowledge, precise numerical calculations, and strict adherence to complian…

Math

Simple o3: Towards Interleaved Vision-Language Reasoning

2025-08-16 · Ye Wang, Qianglong Chen, Zejun Li, Siyuan Wang 외 arxiv

Multimodal Large Language Models (MLLMs) have shown impressive performance on vision-language tasks, but their long Chain-of-Thought (CoT) capabilities in multimodal scenarios remain underexplored. Inspired by OpenAI's o…

Multimodal ReasoningVisual GroundingVisual ReasoningImage Cropping

DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning

2026-05-28 · Yang He, Xiao Ding, Bibo Cai, Yufei Zhang 외 arxiv

Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation required for strategic planning and self-cor…

Reinforcement Learning

AIR: Adaptive Interleaved Reasoning with Code in MLLMs

2026-06-22 · Cong Han, Xiaohan Lan, Haibo Qiu, Yujie Zhong arxiv

Following the paradigm shift initiated by OpenAI o3, interleaved reasoning with code to enhance multimodal large language models (MLLMs) has become a pivotal research frontier. The existing literature focuses primarily o…

Reinforcement Learning

InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward

2026-05-26 · Zhiwei Ning, Wenwen Tong, Xiangli Kong, Shengnan Ma 외 arxiv

While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-centric paradigm, limiting their applicabili…

Reinforcement LearningLogical ReasoningVisual Reasoning