@inproceedings{site-etal-2026-itunlp,
    title = "{ITUNLP} at {MWE}-2026 {A}d{MIR}e 2: A Zero-Shot {LLM} Pipeline for Multimodal Idiom Understanding and Ranking",
    author = {Site, Atakan  and
      Arslan, O{\u{g}}uz Ali  and
      Eryi{\u{g}}it, G{\"u}l{\c{s}}en},
    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-1.30/",
    pages = "226--236",
    ISBN = "979-8-89176-363-0",
    abstract = "This paper presents our system for AdMIRe 2 (Advancing Multimodal Idiomaticity Representation), a shared task on multilingual multimodal idiom understanding. The task focuses on ranking images according to how well they depict the literal or idiomatic usage of potentially idiomatic expressions (PIEs) in context, across 15 languages and two tracks: a text-only track, and a multimodal track that uses both images and captions. To tackle both tracks, we propose a hybrid zero-shot pipeline built on large vision{--}language models (LVLMs). Our system employs a chain-of-thought prompting scheme that first classifies each PIE usage as literal or idiomatic and then ranks candidate images by their alignment with the inferred meaning.A primary{--}fallback routing mechanism increases robustness to safety-filter refusals, while lightweight post-processing recovers consistent rankings from imperfect model outputs.Without any task-specific fine-tuning, our approach achieves 55.9{\%} Top-1 Accuracy in the text-only track and 60.1{\%} in the multimodal (text+image) track, ranking first overall on the official leaderboard. These results suggest that carefully designed zero-shot LVLM pipelines can provide strong baselines for multilingual multimodal idiomaticity benchmarks."
}