@inproceedings{iyengar-etal-2026-diagrams,
    title = "{DIAGRAMS} : A Review Framework for Reasoning-Level Attribution in Diagram {QA}",
    author = "Iyengar, Anirudh Iyengar Kaniyar Narayana  and
      Kumar, Tampu Ravi  and
      Suri, Manan  and
      Bommireddy, Raviteja  and
      Manocha, Dinesh  and
      Mathur, Puneet  and
      Gupta, Vivek",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.76/",
    pages = "774--784",
    ISBN = "979-8-89176-392-0",
    abstract = "Diagram question answering (Diagram QA) requires reasoning-level attribution that links each question-answer pair to all visual regions needed to derive the answer, rather than only the region containing the final response. Creating such structured evidence across diagrams, charts, maps, circuits, and infographics is time-consuming, and existing annotation tools tightly couple their interfaces to dataset-specific formats. We present **DIAGRAMS**, a lightweight, schema-driven review framework that decouples interface logic from dataset-specific JSON structures through an internal meta-schema and dataset adapters. Given an image and QA pair with optional candidate regions, the system performs QA-conditioned evidence selection and proposes the regions required for reasoning. When QA pairs or candidate regions are missing, it generates them and supports human verification and refinement. Across six Diagram QA datasets, model-suggested evidence achieves 85.39{\%} precision and 75.30{\%} recall against reviewer-final selections (micro-averaged). These results indicate that the review-first framework reduces the number of regions that annotators must create from scratch. Human reviewers accept, edit, or reject each proposed region before export, which structurally limits over-reliance on AI proposals. We release a public demo and installable package to support dataset auditing, grounded supervision creation, and grounded evaluation."
}