analiza aiqbench
This arXiv paper benchmarks 13 explainability methods and 17 evaluation metrics on multimodal document-understanding models, which combine text, layout, and images. Its most useful finding for practitioners is that few methods perform consistently across criteria, with Occlusion ranking best overall, and that some faithfulness and complexity metrics give unreliable results. Readers building or auditing document AI in high-stakes settings should note that the work is a research benchmark on explanation quality, not evidence that the explanations are sufficient for real-world accountability.
DocXEval: A Systematic Evaluation of Explainability in Multimodal Document Understanding
arXiv:2610.36929v1 Announce Type: new 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 https://github.com/saifullah3396/docxeval/.
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.
Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2610.36929 [cs.CL]
(or arXiv:2610.36929v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2610.36929 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 337 cuvinte
Subiecte conexe
Dependencies in conversation and in software
LessWrong · 29 oct. 2026
Challenges of Explainability in Continual Learning for Time Series Forecasting
arXiv · 23 iul. 2026
Regional Explanations via Causal Sufficiency and Necessity
arXiv · 17 sept. 2026
Enhancing Visual Feature Attribution via Weighted Integrated Gradients
arXiv · 16 iun. 2026