M$^3$-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering

• URL: http://arxiv.org/abs/2604.25122v1
• Date: Tue, 28 Apr 2026 01:57:22 GMT
• Title: M$^3$-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering
• Abstract summary: M$3$-VQA is a knowledge-based Visual Question Answering (VQA) benchmark.<n>It introduces diverse multi-entity questions involving multiple distinct entities from both visual and textual sources.<n>It requires models to perform both sequential and parallel multi-hop reasoning across multiple documents.
• Score: 16.14696376349009
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning. Unlike existing VQA datasets that focus on coarse-grained categories and simple reasoning over single entities, M$^3$-VQA introduces diverse multi-entity questions involving multiple distinct entities from both visual and textual sources. It requires models to perform both sequential and parallel multi-hop reasoning across multiple documents, supported by traceable, detailed evidence and a curated multimodal knowledge base. We evaluate 16 leading MLLMs under three settings: without external knowledge, with gold evidence, and with retrieval-augmented input. The poor results reveal significant challenges for MLLMs in knowledge acquisition and reasoning. Models perform poorly without external information but improve markedly when provided with precise evidence. Furthermore, reasoning-aware agentic retrieval surpasses heuristic methods, highlighting the importance of structured reasoning for complex multimodal understanding. M$^3$-VQA presents a more challenging evaluation for advancing the multimodal reasoning capabilities of MLLMs. Our code and dataset are available at https://github.com/CASIA-IVA-Lab/M3VQA.

Related papers

• M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation [20.170643730917963]
  M$3$KG-RAG is a Multi-hop Multimodal Knowledge Graph-enhanced RAG.<n>It retrieves query-aligned audio-visual knowledge from MMKGs.<n>It improves reasoning depth and answer faithfulness in MLLMs.
  arXiv  Detail & Related papers  (2025-12-23T07:54:03Z)
• Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective [42.832839189236694]
  We propose MAMMQA, a multi-agent QA framework for multimodal inputs spanning text, tables, and images.<n>Our system includes two Visual Language Model (VLM) agents and one text-based Large Language Model (LLM) agent.<n> Experiments on diverse multimodal QA benchmarks demonstrate that our cooperative, multi-agent framework consistently outperforms existing baselines in both accuracy and robustness.
  arXiv  Detail & Related papers  (2025-05-27T07:23:38Z)
• Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering [60.062194349648195]
  Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents.<n>Current document retrieval-augmented generation (DocRAG) methods remain limited by their text-centric approaches.<n>We introduce MMDocRAG, a comprehensive benchmark featuring 4,055 expert-annotated QA pairs with multi-page, cross-modal evidence chains.
  arXiv  Detail & Related papers  (2025-05-22T09:52:57Z)
• Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts [56.7225771305861]
  This paper introduces Multi-Modal Retrieval-Augmented Generation (M$2$RAG), a benchmark designed to evaluate the effectiveness of Multi-modal Large Language Models.<n>The benchmark comprises four tasks: image captioning, multi-modal question answering, multi-modal fact verification, and image reranking.<n>To enhance the context utilization capabilities of MLLMs, we also introduce Multi-Modal Retrieval-Augmented Instruction Tuning (MM-RAIT)
  arXiv  Detail & Related papers  (2025-02-24T16:25:25Z)
• MMRel: A Relation Understanding Benchmark in the MLLM Era [72.95901753186227]
  Multi-Modal Relation Understanding (MMRel) is a benchmark that features large-scale, high-quality, and diverse data on inter-object relations. MMRel is ideal for evaluating MLLMs on relation understanding, as well as for fine-tuning MLLMs to enhance relation comprehension capability.
  arXiv  Detail & Related papers  (2024-06-13T13:51:59Z)
• Needle In A Multimodal Haystack [79.81804334634408]
  We present the first benchmark specifically designed to evaluate the capability of existing MLLMs to comprehend long multimodal documents. Our benchmark includes three types of evaluation tasks: multimodal retrieval, counting, and reasoning. We observe that existing models still have significant room for improvement on these tasks, especially on vision-centric evaluation.
  arXiv  Detail & Related papers  (2024-06-11T13:09:16Z)
• MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI [71.53579367538725]
  MMT-Bench is a benchmark designed to assess Large Vision-Language Models (LVLMs) across massive multimodal tasks. MMT-Bench comprises $31,325$ meticulously curated multi-choice visual questions from various multimodal scenarios.
  arXiv  Detail & Related papers  (2024-04-24T17:37:05Z)
• Generative Multi-Modal Knowledge Retrieval with Large Language Models [75.70313858231833]
  We propose an innovative end-to-end generative framework for multi-modal knowledge retrieval. Our framework takes advantage of the fact that large language models (LLMs) can effectively serve as virtual knowledge bases. We demonstrate significant improvements ranging from 3.0% to 14.6% across all evaluation metrics when compared to strong baselines.
  arXiv  Detail & Related papers  (2024-01-16T08:44:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.