# MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use Source: [MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use]() Collection index: [llms.txt]() Data updated: 2025-11-26T05:05:12.736Z Authors: Ahmad Mohammadshirazi, Pinaki Prasad Guha Neogi, Dheeraj Kulshrestha, Rajiv Ramnath Published: 2025-11-22T02:17:42.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()