@inproceedings{umut-senceylan-2026-itunlp2,
    title = "{ITUNLP}2 at {MWE}-2026 {A}d{MIR}e 2: Modular Zero-Shot Pipelines for Multimodal Idiom Grounding and Ranking",
    author = {Umut, {\"O}zge  and
      {\c{S}}enceylan, Bora},
    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-1.32/",
    pages = "248--253",
    ISBN = "979-8-89176-363-0",
    abstract = "We describe a zero-shot system for AdMIRe 2.0, a shared task on multimodal understanding of potentially idiomatic expressions (PIEs). Given a context sentence with a PIE and five candidate images, the system predicts whether the usage is literal or idiomatic and ranks images by how well they match the intended meaning. We use closed-source large multimodal models and compare prompting pipelines from direct one-step ranking to modular multi-step pipelines that separate sense prediction, PIE-focused image semantics, and final ranking. All steps produce constrained JSON outputs to enable deterministic parsing and composition. In the official AdMIRe 2.0 evaluation on CodaBench, our best pipeline achieves an average Top-1 accuracy of 0.52 and an average nDCG score of 0.70 across the 12 languages we submitted. We obtain the best score among submitted systems in 10 of these languages."
}