让文档问答模型不仅答得准，还能自动生成有依据的可视化解释。
DocVXQA: Context-Aware Visual Explanations for Document Question Answering
- 通过显式学习目标融合解释机制，生成上下文相关的热力图。
- 解释区域既完整又精简，兼顾准确率与可解释性。
- 适合需要透明决策过程的文档分析场景，如金融、法律审核。
我们提出 DocVXQA，一种面向文档问答任务的视觉自解释新框架。该框架不仅能给出准确答案，还能学习生成突出上下文关键区域的视觉热力图，为模型决策提供可解释的依据。为将解释融入训练过程，我们定量定义可解释性原则作为显式学习目标。与仅关注答案相关区域的传统方法不同，本框架生成的解释具备上下文充分性且表示高效，有助于提升用户信任，在预测性能与可解释性间取得平衡。大量实验（含人工评估）充分验证了方法的有效性。代码已开源：https://github.com/dali92002/DocVXQA。
原文摘要 · Abstract (English)
We propose DocVXQA, a novel framework for visually self-explainable document question answering. The framework is designed not only to produce accurate answers to questions but also to learn visual heatmaps that highlight contextually critical regions, thereby offering interpretable justifications for the model's decisions. To integrate explanations into the learning process, we quantitatively formulate explainability principles as explicit learning objectives. Unlike conventional methods that emphasize only the regions pertinent to the answer, our framework delivers explanations that are \textit{contextually sufficient} while remaining \textit{representation-efficient}. This fosters user trust while achieving a balance between predictive performance and interpretability in DocVQA applications. Extensive experiments, including human evaluation, provide strong evidence supporting the effectiveness of our method. The code is available at https://github.com/dali92002/DocVXQA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。