@inproceedings{islam-erana-2026-cognac,
    title = "{COGNAC} at {S}em{E}val-2026 Task 5: {LLM} Ensembles for Human-Level Word Sense Plausibility Rating in Challenging Narratives",
    author = "Islam, Azwad Anjum  and
      Erana, Tisa Islam",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.414/",
    pages = "3328--3336",
    ISBN = "979-8-89176-414-9",
    abstract = "We present a system for SemEval-2026 Task 5 that predicts 1{--}5 plausibility ratings for candidate senses of homonyms in ambiguous short stories using prompting with closed-source LLMs. We evaluate three prompting strategies: zero-shot, chain-of-thought, and comparative prompting that jointly scores competing senses. We also find simple unweighted ensembling better aligns with subjective human judgments better than individual models. Our official submission ranked 4th on the leaderboard with an average score of 0.86, with post-competition experiments improving performance to 0.89."
}