@inproceedings{goyal-etal-2026-paradise,
    title = "Paradise at {S}em{E}val-2026 Task 12: Leveraging Instruction-Tuned Large Language Models with Chain-of-Thought Prompting for Abductive Event Reasoning",
    author = "Goyal, Dhruv  and
      Gupta, Ishita  and
      Bedi, Jatin",
    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-1.100/",
    pages = "706--712",
    ISBN = "979-8-89176-414-9",
    abstract = "We present Paradise, our system for SemEval-2026 Task 12: Abductive Event Reasoning, which identifies plausible direct causes of real-world English-language events using retrieved contextual documents. Our approach employs Qwen2.5-7B-Instruct, a 7-billion-parameter instruction-tuned language model combined with carefully engineered chain-of-thought prompting, requiring no task-specific fine-tuning or training-data supervision (prompt components were selected using the development set). The system achieves a score of 0.79 on the official 612-instance test set by integrating explicit causal-inference rules, 4,000-character document context windows, and greedy decoding. Analysis reveals that conservative prediction patterns, 87.1{\%} single-label and 36.9{\%} Option D, effectively exploit the asymmetric scoring metric. Ablation studies confirm that document context contributes +6.4 points, chain-of-thought reasoning +5.3 points, and explicit causal rules +3.1 points to development performance. Our code is publicly available at https://github.com/DhruvGoyal404/semeval2026-task12."
}