@inproceedings{kawada-holyoak-2026-cascademind,
    title = "{C}ascade{M}ind at {S}em{E}val-2026 Task 4: A Hybrid Neuro-Symbolic Cascade for Narrative Similarity",
    author = "Kawada, Sebastien  and
      Holyoak, Dylan",
    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-1.204/",
    pages = "1575--1581",
    ISBN = "979-8-89176-414-9",
    abstract = "Across self-consistency samples from an LLM, vote agreement tracks instance difficulty: on SemEval-2026 Task 4 (Narrative Story Similarity), supermajority cases ({\ensuremath{\geq}} 7/8 votes) resolve at 85{\%} accuracy, split votes at 67{\%}, and perfect ties at 61{\%}, a monotone gradient that holds across the development set. We exploit this in CascadeMind, which routes eight Gemini 2.5 Flash votes by consensus, escalates split votes to additional sampling rounds, and falls through to a symbolic ensemble of theory-inspired narrative signals only on perfect ties (5{\%} of cases). The system reached 72.75{\%} on Track A test, placing 10th of 44 teams. Ablations show that the symbolic component contributes negligibly end-to-end and that nearly all gains come from confidence-aware routing. The takeaway is methodological: for narrative similarity, calibrating when to spend more compute on a hard instance matters more than adding auxiliary representations to reason about it. Code is available at https://github.com/chreia/CascadeMind-ACL."
}