arXiv cs.CL· Saifullah Saifullah, David Dembinsky, Stefan Agne, Andreas Dengel, Sheraz Ahmed·· 13 小时前AI 评分31
DocXEval：多模态文档理解可解释性系统评测框架
DocXEval: A Systematic Evaluation of Explainability in Multimodal Document Understanding
AI 导读
研究者提出 DocXEval，首个面向多模态（文本、布局、图像）文档理解的可解释性框架，将现有 XAI 方法与评测指标适配到该场景。该框架系统评测了 13 种 XAI 方法，覆盖 3 项文档理解任务、8 个数据集、4 个模型和 17 项指标，发现仅少数方法在各标准下表现一致，Occlusion 整体上最忠实、最可解释。
正文 · 原文
Abstract:Multimodal transformer models have driven unprecedented performance breakthroughs in modern document understanding. However, the inherent black-box nature of these models remains a major obstacle to their safe deployment in high-stakes sectors. Despite significant progress in explainability for vision and language tasks, explainable AI (XAI) research tailored to multimodal document understanding has received little attention. To address this gap, we present \ourframework{}, the first comprehensive explainability framework that adapts existing XAI methods and evaluation metrics to the multimodal (text, layout, and image) document understanding context, while introducing efficient multi-target adaptations of both methods and metrics for domain-specific tasks such as semantic entity recognition. Using \ourframework{}, we systematically evaluate 13 XAI methods across 3 document understanding tasks, 8 datasets, 4 models, and 17 evaluation metrics, and find that only a few methods perform consistently across all evaluation criteria, with Occlusion emerging as the most faithful and interpretable method overall. Through a dedicated meta-evaluation, we observe moderate to strong agreement among several faithfulness and complexity metrics while identifying certain ones that produce unreliable results. Finally, through multiple dataset-wide diagnostic analyses, we uncover key insights into model behavior, including the contribution of individual modalities across tasks and labels, spatial attribution patterns around target entities, and potential dataset biases. Overall, this work serves as both a benchmark and a practical guide for future XAI research in multimodal document understanding. To support reproducibility, we publicly release our code at this https URL.
| Subjects: | Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.36929 [cs.CL] |
| (or arXiv:2610.36929v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36929 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Saifullah Saifullah [view email]
[v1]
Tue, 27 Oct 2026 09:53:21 UTC (30,463 KB)
来源：arXiv cs.CL · arxiv.org