@inproceedings{ye-etal-2025-knowledge,
    title = "Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language Models",
    author = "Ye, Guanghui  and
      Zhao, Huan  and
      Zhao, Zhixue  and
      Zha, Xupeng  and
      Liu, Yang  and
      Jiang, Zhihua",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1063/",
    pages = "21883--21896",
    ISBN = "979-8-89176-251-0",
    abstract = "We revisit knowledge-based visual reasoning (KB-VR) in light of modern advances in multimodal large language models (MLLMs), and make the following contributions: (i) We propose Visual Knowledge Card (VKC) {--} a novel image that incorporates not only internal visual knowledge (e.g., scene-aware information) detected from the raw image, but also external world knowledge (e.g., attribute or object knowledge) produced by a knowledge generator; (ii) We present VKC-based Multi-Image Reasoning (VKC-MIR) {--} a four-stage pipeline which harnesses a state-of-the-art scene perception engine to construct an initial VKC (Stage-1), a powerful LLM to generate relevant domain knowledge (Stage-2), an excellent image editing toolkit to introduce generated knowledge into the updated VKC (Stage-3), and finally, an emerging multi-image MLLM to solve the VKC-enhanced task (Stage-4). By performing experiments on three popular KB-VR benchmarks, our approach achieves new state-of-the-art results compared to previous top-performing models."
}