Year: 2026
Type: conference-paper
Abstract: Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowledge beyond directly observable content in images.While recent multi modal large language models (MLLMs) show strong perceptual abilities, they struggle on KB-VQA tasks requiring groundings from both finegrained entity and evidence levels.Most existing multi-modal retrieval augmented generation (MM-RAG) methods tightly couple entity discrimination and section-level evidence ranking into a single re-ranking stage, leading to high cost and limited generalization.In this work, we revisit existing MM-RAG solutions from a workflow perspective and argue both entity-level and fact-level groundings are key bottlenecks.We observe that although MLLMs often fail under open-ended entity naming, they can better identify the correct entity when selecting from a small set of candidate names.Based on this insight, we propose a simple and training-free identify-before-answer IBA framework that decouples entity identification from section-level re-ranking.Our approach prompts an MLLM to select high-confidence entities using only candidate names, followed by an off-the-shelf textual re-ranker for evidence selection.Experiments on Encyclopedic-VQA and InfoSeek show that our method consistently outperforms fine-tuned multi-modal re-ranking baselines while reducing training and inference complexity.Additional analyses reveal that the improvements arise not only from better entity identification, but also from selecting more informative evidence once correct entity is fixed.Our implementation is made public to ease reproducibility https
Authors: Qian Ma, Qiong Wu, Zhengyi Zhou, Yao Ma
Institutions: Rensselaer Polytechnic Institute, AT&T (United States)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: National Science Foundation
Awards: CRII:III:Towards Advanced Filtering and Pooling Operations for Graph Neural Networks, Collaborative Research: III: Medium: Graph Neural Networks for Heterophilous Data: Advancing the Theory, Models, and Applications, Category I: Crossing the Divide Between Today's Practice and Tomorrow's Science
OpenAlex ID: W7166839408