DocCogito: 对齐布局认知与分步 grounded 推理以实现文档理解
DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding
AI总结：
DocCogito通过整合布局感知与结构化推理，提升文档理解的准确性和推理过程的系统性。
摘要：
文档理解需要多模态大语言模型（MLLMs）不仅提供准确答案，还需要显式的、基于证据的推理，尤其是在高风险场景中。然而，当前的文档MLLMs在形成完整的、类人推理过程方面仍存在不足，因为即使它们在布局编码和CoT式提示方面有所改进，布局与推理之间的交互通常是隐式学习的，仍然松散耦合，而非被强制作为系统机制。因此，我们提出了DocCogito，一个统一的框架，将全局布局感知与结构化、区域基础的推理相结合。DocCogito引入了一个轻量级的布局塔，将页面结构转化为可学习的全局布局先验标记，并引入了确定性的视觉-语义链（VSC）——一种比自由形式自然语言CoT更清晰的结构化表示，以监督与证据区域对齐的细粒度中间推理。训练遵循渐进式配方，包括布局感知预训练、VSC引导的冷启动、拒绝采样和GRPO。为进一步加强布局先验与VSC执行之间的内部耦合，我们增强了标准奖励，加入细粒度区域置信度信号，以鼓励推理轨迹保持与相应证据区域对齐。在六个基准（DocVQA、WTQ、ChartQA、TextVQA、OCRBench和InfoVQA）上的广泛实验表明，该方法具有强大的泛化能力，在四个基准上实现了最先进的结果。
英文摘要：
Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes scenarios. However, current document MLLMs still fall short of forming a complete, human-like reasoning process, because even when they improve both layout encoding and CoT-style prompting, the interaction between the two is typically learned implicitly and remains loosely coupled rather than being enforced as a systematic mechanism. So we propose DocCogito, a unified framework that integrates global layout perception with structured, region-grounded reasoning. DocCogito introduces a lightweight layout tower that distills page structure into learnable global layout prior tokens, and a deterministic Visual-Semantic Chain (VSC)-a concise structured representation less ambiguous than free-form natural-language CoT-to supervise fine-grained intermediate reasoning aligned with evidence regions. Training follows a progressive recipe, including layout perception pretraining, VSC-guided cold start, rejection sampling, and GRPO. To further strengthen the internal coupling between layout priors and VSC execution, we augment standard rewards with a fine-grained region-confidence signal that encourages reasoning traces to stay aligned with corresponding evidence regions. Extensive experiments on six benchmarks (DocVQA, WTQ, ChartQA, TextVQA, OCRBench, and InfoVQA) demonstrate strong generalization, achieving state-of-the-art results on four benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
