# MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models Source: [MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:21:39.376Z Authors: Wenbo Hu, Jia-Chen Gu, Zi-Yi Dou, Mohsen Fayyaz, Pan Lu, Kai-Wei Chang, Nanyun Peng Published: 2024-10-10T17:55:02.000Z ## Abstract Existing multimodal retrieval benchmarks primarily focus on evaluating whether models can retrieve and utilize external textual knowledge for question answering. However, there are scenarios where retrieving visual information is either more beneficial or easier to access than textual data. In this paper, we introduce a multimodal retrieval-augmented generation benchmark, MRAG-Bench, in which we systematically identify and categorize scenarios where visually augmented knowledge is better than textual knowledge, for instance, more images from varying viewpoints. MRAG-Bench consists of 16,130 images and 1,353 human-annotated multiple-choice questions across 9 distinct scenarios. With MRAG-Bench, we conduct an evaluation of 10 open-source and 4 proprietary large vision-language models (LVLMs). Our results show that all LVLMs exhibit greater improvements when augmented with images compared to textual knowledge, confirming that MRAG-Bench is vision-centric. Additionally, we conduct extensive analysis with MRAG-Bench, which offers valuable insights into retrieval-augmented LVLMs. Notably, the top-performing model, GPT-4o, faces challenges in effectively leveraging retrieved knowledge, achieving only a 5.82% improvement with ground-truth information, in contrast to a 33.16% improvement observed in human participants. These findings highlight the importance of MRAG-Bench in encouraging the community to enhance LVLMs' ability to utilize retrieved visual knowledge more effectively. ## 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. - [Vision-centric Visual Question Answering on MRAG-Bench (test)](): Vision-centric Visual Question Answering; MRAG-Bench (test); Angle Robustness Score: 61.18. ## Original sources and implementation [Original paper]() [PDF]()