@inproceedings{terao-tachioka-2026-itlab,
    title = "d-itlab at {S}em{E}val-2026 Task 12: Per-Option Surprisal and Multi-Stage Gating for Precision-Oriented Causal Reasoning",
    author = "Terao, Yasunori  and
      Tachioka, Yuuki",
    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-1.228/",
    pages = "1791--1801",
    ISBN = "979-8-89176-414-9",
    abstract = "We describe the system submitted by d-itlab to SemEval-2026 Task{\textasciitilde}12 (Abductive Event Reasoning), which requires selecting the most plausible direct cause(s) of an observed event from candidate options grounded in reference documents. Our approach combines (i) per-option multi-stage LLM inference that evaluates each option independently with progressively stricter verification, (ii) surprisal-based features obtained by teacher-forcing candidate sentences and measuring token-level negative log-likelihood, and (iii) an XGBoost ensemble trained on these heterogeneous features to produce a precision-oriented final prediction. In the official test set, our system scored 0.91, ranking third among 116 participating teams."
}