CURV：通过课程化视觉基础推理增强图表理解

摘要

图表问答（CQA）要求多模态大语言模型（MLLMs）将视觉理解与逻辑推理相结合，然而当前模型难以实现精确的视觉定位和连贯的推理链。尽管外部思维链提示和视觉线索能够显著提升性能，但现有MLLMs缺乏内在的视觉基础推理能力，导致感知不准确以及推理与视觉证据相脱节。为克服这些局限，我们提出CURV——一种课程学习框架，通过将CQA重构为多步视觉基础推理来培养内在的视觉推理能力，其中每一步通过空间注意力集中将逻辑推理与动态视觉定位相协调。为辅助模型学习，我们进一步引入CCQA，一个包含三个级别的课程数据集，具备跨多样图表类型和推理模式的可扩展合成生成能力。该课程系统性地从基础的单操作推理逐步过渡到复杂的多图表组合任务。实验表明，CURV相较于基线模型实现了高达20.50%的性能提升，并且能够泛化到真实世界基准（最高提升12.30%）和跨领域多模态推理任务（最高提升10.20%），从而验证了通过动态定位内化视觉推理以增强图表理解能力的有效性。代码已在 https://xhguo7.github.io/CURV/ 提供。

English

Chart question answering (CQA) requires multimodal large language models (MLLMs) to integrate visual comprehension with logical reasoning, yet current models struggle with accurate visual grounding and coherent reasoning chains. While extrinsic chain-of-thought prompting and visual cues significantly improve performance, current MLLMs lack intrinsic visual grounded reasoning capabilities, leading to inaccurate perception and reasoning disconnected from visual evidence. To address these limitations, we propose CURV, a curriculum learning framework that develops intrinsic visual reasoning capabilities by reformulating CQA as multi-step visual grounded reasoning, where each step coordinates logical reasoning with dynamic visual grounding through spatial attention concentration. To assist model learning, we further introduce CCQA, a three-level curriculum dataset with scalable synthetic generation across diverse chart types and reasoning patterns. Our curriculum systematically progresses from basic single-operation reasoning to complex multi-chart compositional tasks. Experiments demonstrate that CURV achieves up to uparrow20.50% improvements over baselines and is generalizable to real-world benchmarks (up to uparrow12.30%) and out-of-domain multimodal reasoning tasks (up to uparrow10.20%), validating the effectiveness of internalizing visual reasoning with dynamic grounding for enhanced chart understanding capabilities. Code is available at: https://xhguo7.github.io/CURV/.