@inproceedings{komurcu-temel-2026-3k2t,
    title = "3{K}2{T} at {MWE}-2026 {A}d{MIR}e 2: {CARIM}{--} Category-Aware Reasoning for Idiomatic Multimodality",
    author = {K{\"o}m{\"u}rc{\"u}, Kubilay Ka{\u{g}}an  and
      Temel, Tugce},
    editor = {Ojha, Atul Kr.  and
      Mititelu, Verginica Barbu  and
      Constant, Mathieu  and
      Stoyanova, Ivelina  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Rademaker, Alexandre},
    booktitle = "Proceedings of the 22nd Workshop on Multiword Expressions ({MWE} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Marocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.mwe-1.21/",
    pages = "160--164",
    ISBN = "979-8-89176-363-0",
    abstract = "Idiomatic expressions pose a fundamental challenge for multimodal understanding due to their non-compositional semantics, while pretrained vision{--}language models tend to over-rely on literal visual alignments. We address this issue in the context of the AdMIRe 2.0 multimodal idiomatic image ranking task by introducing CARIM (Category-Aware Reasoning for Idiomatic Multimodality), an inference-time framework that injects structured semantic reasoning without end-to-end retraining.Experiments on the official Codabench leaderboard demonstrate that CARIM achieves competitive Top-1 Accuracy and nDCG across multiple languages. Additional post-competition evaluation on the released test annotations further shows that CARIM maintains robust multilingual performance, highlighting the effectiveness of inference-time category-aware reasoning for multimodal idiomatic grounding."
}