@inproceedings{karafyllis-etal-2026-ails,
    title = "{AILS}-{NTUA} at {S}em{E}val-2026 Task 12: Graph-Based Retrieval and Reflective Prompting for Abductive Event Reasoning",
    author = "Karafyllis, Nikolaos  and
      Lymperaiou, Maria  and
      Filandrianos, Giorgos  and
      Voulodimos, Athanasios  and
      Stamou, Giorgos",
    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-1.252/",
    pages = "1997--2019",
    ISBN = "979-8-89176-414-9",
    abstract = "We present a winning three-stage system for SemEval 2026 Task 12: Abductive Event Reasoning that combines graph-based retrieval, LLM-driven abductive reasoning with prompt design informed by reflective prompt evolution, and post-hoc consistency enforcement; our system ranks first on the evaluation-phase leaderboard with an accuracy score of 0.95. Cross-model error analysis across 14 models (7 families) reveals three shared inductive biases: causal chain incompleteness, proximate cause preference, and salience bias, whose cross-family convergence (51{\%} cause-count reduction) indicates systematic rather than model-specific failure modes in multi-label causal reasoning."
}