@inproceedings{kangur-etal-2025-multireflect,
    title = "{M}ulti{R}eflect: Multimodal Self-Reflective {RAG}-based Automated Fact-Checking",
    author = "Kangur, Uku  and
      Agrawal, Krish  and
      Singh, Yashashvi  and
      Sabir, Ahmed  and
      Sharma, Rajesh",
    editor = "Kriz, Reno  and
      Murray, Kenton",
    booktitle = "Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.magmar-1.1/",
    pages = "1--17",
    ISBN = "979-8-89176-280-0",
    abstract = "In this work, we introduce MultiReflect, a novel multimodal self-reflective Retrieval Augmented Generation (RAG)-based automated fact-checking pipeline. MultiReflect is designed to address the challenges of rapidly outdated information, limitations in human query capabilities, and expert knowledge barriers in fact-checking. Our proposed pipeline leverages the latest advancements in Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) to enhance fact verification across text and images. Specifically, by integrating multimodal data processing with RAG-based evidence reflection, our system improves the accuracy of fact-checking by utilizing internet-sourced verification. We evaluate our results on the VERITE benchmarks and using several multimodal LLMs, outperforming baselines in binary classification."
}