@inproceedings{antonelli-dziri-etal-2026-guysllm,
    title = "{G}uys{LLM} at {S}em{E}val-2026 Task 5: {NLI}-Informed Regression for Graded Word-Sense Plausibility in Narrative Contexts",
    author = "Antonelli-Dziri, Niccol{\'o}  and
      Marcotte, Sixtine  and
      Rosapepe, Emanuele  and
      Santona, Gabriele  and
      Wafaay, Omar  and
      Vaiani, Lorenzo  and
      Coppola, Riccardo  and
      Giobergia, Flavio",
    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-1.314/",
    pages = "2487--2494",
    ISBN = "979-8-89176-414-9",
    abstract = "While large language models (LLMs) excel at semantic reasoning, their discrete token-based outputs introduce limitations for fine-grained regression tasks requiring continuous scoring. We address graded word-sense plausibility estimation by reformulating it as a Natural Language Inference (NLI) regression problem, adapting DeBERTa-v3-large with NLI pretraining and a regression head to predict continuous plausibility scores from story-sense pairs. We compare this model against BERT, vanilla DeBERTa, SmolLM variants and state-of-the art LLMs under various prompting strategies, and show that the NLI-finetuned model achieves superior rank correlation and alignment with human judgments. While several baselines collapse toward mean predictions and LLMs show unstable prompting sensitivity, our findings establish NLI-informed pretraining as highly effective for narrative plausibility regression, highlighting fundamental LLM limitations for word sense disambiguation."
}