@inproceedings{sravanthi-etal-2025-rg,
    title = "{RG}-{VQA}: Leveraging Retriever-Generator Pipelines for Knowledge Intensive Visual Question Answering",
    author = "Sravanthi, Settaluri Lakshmi  and
      Agarwal, Pulkit  and
      Mondal, Debjyoti  and
      Singh, Rituraj  and
      Panda, Subhadarshi  and
      Mishra, Ankit  and
      Pradeep, Kiran  and
      B, Srihari K  and
      Rao, Godawari Sudhakar  and
      Bhattacharyya, Pushpak",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1306/",
    doi = "10.18653/v1/2025.findings-emnlp.1306",
    pages = "24048--24060",
    ISBN = "979-8-89176-335-7",
    abstract = "In this paper, we propose a method to improve the reasoning capabilities of Visual Question Answering (VQA) systems by integrating Dense Passage Retrievers (DPRs) with Vision Language Models (VLMs). While recent works focus on the application of knowledge graphs and chain-of-thought reasoning, we recognize that the complexity of graph neural networks and end-to-end training remain significant challenges. To address these issues, we introduce **R**elevance **G**uided **VQA** (**RG-VQA**), a retriever-generator pipeline that uses DPRs to efficiently extract relevant information from structured knowledge bases. Our approach ensures scalability to large graphs without significant computational overhead. Experiments on the ScienceQA dataset show that RG-VQA achieves state-of-the-art performance, surpassing human accuracy and outperforming GPT-4 by more than . This demonstrates the effectiveness of RG-VQA in boosting the reasoning capabilities of VQA systems and its potential for practical applications."
}