@inproceedings{prasad-etal-2026-clutch,
    title = "Clutch or Cry at {S}em{E}val-2026 Task 12: Offline Retrieval-Augmented Generation with Frozen {D}e{BERT}a for Abductive Event Reasoning",
    author = "Prasad, Aayush  and
      Trivedi, Rudra  and
      Khatib, Arshad  and
      Malviya, Shrikant  and
      Kumar, Naveen",
    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-1.261/",
    pages = "2078--2081",
    ISBN = "979-8-89176-414-9",
    abstract = "We present our system for SemEval-2026 Task 12 on abductive event reasoning. Initial experiments with direct fine-tuning of large language models suffered from severe overfitting due to limited training data, while smaller models failed under context-length constraints, leading to random guessing under the strict Exact Match evaluation metric. To address these challenges, we propose a two-stage offline Retrieval-Augmented Generation (RAG) pipeline that separates semantic evidence retrieval from multi-label classification. We employ a dense retriever (all-MiniLM-L6-v2) to extract the single most relevant sentence (top-k=1) and feed it into a partially frozen DeBERTa-v3-Large classifier trained with BCEWithLogitsLoss. Freezing the lower 12 layers effectively mitigates overfitting while preserving pre-trained semantic knowledge. Our approach eliminates long-context truncation issues, reduces hallucination, and achieves a final Exact Match accuracy of 0.72 on the official test set."
}