{"ID":2838163,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17881","arxiv_id":"2511.17881","title":"MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use","abstract":"Document Visual Question Answering (DocVQA) requires models to jointly understand textual semantics, spatial layout, and visual features. Current methods struggle with explicit spatial relationship modeling, inefficiency with high-resolution documents, multi-hop reasoning, and limited interpretability. We propose MGA-VQA, a multi-modal framework that integrates token-level encoding, spatial graph reasoning, memory-augmented inference, and question-guided compression. Unlike prior black-box models, MGA-VQA introduces interpretable graph-based decision pathways and structured memory access for enhanced reasoning transparency. Evaluation across six benchmarks (FUNSD, CORD, SROIE, DocVQA, STE-VQA, and RICO) demonstrates superior accuracy and efficiency, with consistent improvements in both answer prediction and spatial localization.","short_abstract":"Document Visual Question Answering (DocVQA) requires models to jointly understand textual semantics, spatial layout, and visual features. Current methods struggle with explicit spatial relationship modeling, inefficiency with high-resolution documents, multi-hop reasoning, and limited interpretability. We propose MGA-V...","url_abs":"https://arxiv.org/abs/2511.17881","url_pdf":"https://arxiv.org/pdf/2511.17881v1","authors":"[\"Ahmad Mohammadshirazi\",\"Pinaki Prasad Guha Neogi\",\"Dheeraj Kulshrestha\",\"Rajiv Ramnath\"]","published":"2025-11-22T02:17:42Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}