@inproceedings{imani-etal-2026-trace,
    title = "{TRACE}: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models",
    author = "Imani, Shima  and
      Moon, Seungwhan  and
      Mathias, Lambert  and
      Zhang, Lu  and
      Damavandi, Babak",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.166/",
    pages = "3611--3625",
    ISBN = "979-8-89176-380-7",
    abstract = "Reliable mathematical and scientific reasoning remains an open challenge for large vision{--}language models (VLMs). Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce TRACE (Transparent Reasoning And Consistency Evaluation), a framework for analyzing, diagnosing, and improving reasoning in VLMs. At its core, TRACE leverages Auxiliary Reasoning Sets (ARS), compact sub-question{--}answer pairs that decompose complex problems, evaluate intermediate steps through consistency-based metrics, and expose failures overlooked by standard evaluation. Our experiments show that consistency across ARS is linked to final-answer correctness and helps pinpoint the reasoning steps where failures arise, offering actionable signals for model improvement."
}