@inproceedings{asare-aryal-2026-ai4pc,
    title = "{AI}4{PC}-{H}oward {U}niversity at {S}em{E}val-2026 Task 5: Calibrated Hybrid Ensembling and Retrieval-Augmented {LLM} Reasoning for Narrative Word-Sense Plausibility",
    author = "Asare, Kwaku  and
      Aryal, Saurav",
    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-1.326/",
    pages = "2592--2596",
    ISBN = "979-8-89176-414-9",
    abstract = "We present two complementary approaches for rating word-sense plausibility in SemEval-2026 Task 5 (literary homonyms in five-sentence stories). Approach 1 is a retrieve-then-generate pipeline using an open-weight Llama 3.1 70B Instruct model with structured reasoning and a self-correction pass. Approach 2 is a hybrid ensemble that combines API-based LLM prompting with transformer representations and a learned calibration layer trained on the development set. On the development set, Approach 2 achieves Spearman {\ensuremath{\rho}} = 0.7393 (p 10-102) with accuracy 0.8010 (471/588). Approach 1 achieves {\ensuremath{\rho}} = 0.5187 (p 10-65) with accuracy 0.6032 (561/930). We emphasize that Approach 1 does not exceed RoBERTabase in accuracy (0.6032 vs. 0.6410), but provides stronger rank correlation."
}