@inproceedings{ailneni-etal-2026-utd,
    title = "{UTD}-{HLTRI} at {S}em{E}val 2026 Task 4: Reasoning like an Expert for Inferring Narrative Similarity",
    author = "Ailneni, Rakshitha Rao  and
      Bhavsar, Maitry  and
      Harabagiu, Sanda",
    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-1.433/",
    pages = "3508--3519",
    ISBN = "979-8-89176-414-9",
    abstract = "Narrative similarity is a challenging problem that requires reasoning over three aspects of narratives, including (1) the abstract theme; (2) the course of action and (3) the outcomes of narratives. We present UTD.HLTRISIM.NARRATIVES, our method developed for SemEval 2026 Task 4 (Narrative Story Similarity), which combines contrastive reasoning prompting with careful selection of few-shot examples to guide a Large Language Model(LLM) toward decisions of narrative comparative similarity. A curriculum learning framework orders examples of narrative triplets presented to the LLM by using a score that quantifies the impact of common narratives aspects with information discerned from several distractors of narrative similarity between pairs ofnarratives 1."
}