@inproceedings{cotiga-nisioi-2026-dcsn,
    title = "{DCSN}-{NLP} at {MWE}-2026 {A}d{MIR}e 2: Bridging Literal and Figurative Meaning Through Hierarchical Multimodal Reasoning",
    author = "Cotig{\u{a}}, David  and
      Nisioi, Sergiu",
    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-1.29/",
    pages = "217--225",
    ISBN = "979-8-89176-363-0",
    abstract = "This paper presents our system for the MWE-2026 ADMiRe 2.0 shared task, which aimedto advance multimodal idiomatic understand-ing across 15 languages. We address the taskof selecting, from a set of five images, theone that best represents either the literal oridiomatic meaning of a given compound incontext. Our approach follows a multi-steppipeline: a large language model (LLM) firstdetermines whether the compound is used lit-erally or idiomatically and generates auxiliarytext, consisting of an idiomatic meaning expla-nation and a visual description of the literalmeaning. An ensemble of three CLIP modelsthen identifies the two images most semanti-cally similar to the appropriate generated textvia a voting mechanism. Finally, the LLM se-lects the best image from these two candidates."
}