@inproceedings{bakos-etal-2025-generating,
    title = "Generating Spatial Knowledge Graphs from Automotive Diagrams for Question Answering",
    author = "Bakos, Steve  and
      Xing, Chen  and
      Davoudi, Heidar  and
      An, Aijun  and
      DiCarlantonio, Ron",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.157/",
    pages = "2270--2286",
    ISBN = "979-8-89176-333-3",
    abstract = "Answering ``Where is the X button?'' with ``It{'}s next to the Y button'' is unhelpful if the user knows neither location. Useful answers require obvious landmarks as a reference point. We address this by generating from a vehicle dashboard diagram a spatial knowledge graph (SKG) that shows the spatial relationship between a dashboard component and its nearby landmarks and using the SKG to help answer questions. We evaluate three distinct generation pipelines (Per-Attribute, Per-Component, and a Single-Shot baseline) to create the SKG using Large Vision-Language Models (LVLMs). On a new 65-vehicle dataset, we demonstrate that a decomposed Per-Component pipeline is the most effective strategy for generating a high-quality SKG; the graph produced by this method, when evaluated with a novel Significance score, identifies landmarks achieving 71.3{\%} agreement with human annotators. This work enables downstream QA systems to provide more intuitive, landmark-based answers."
}