@inproceedings{sun-etal-2026-ynu,
    title = "{YNU}-{HPCC} at {S}em{E}val-2026 Task 12: Retrieval-Guided Reasoning with Teacher Distillation for Abductive Event Reasoning",
    author = "Sun, Yuwei  and
      Wang, Jin  and
      Zhang, Xuejie",
    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-1.30/",
    pages = "206--212",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper describes the YNU-HPCC system for SemEval-2026 Task 12, Abductive EventReasoning (AER). Given multi-document retrieved evidence with distractors, the task requires selecting all direct-cause options for a target event and outputting an answer set. The main challenges are sparse and dispersed evidence in long documents and a boundary-sensitive set-level evaluation. This paper proposes a two-stage framework. Stage 1 trains a DeBERTa-v3-base student with retrieval-guided evidence modeling: documents are split into overlapping windows, BM25 ranks and filters candidate windows, and Top-K pooling aggregates window-level scores into option probabilities. Stage 2 distills soft targets from a Qwen-14B teacher with temperature scaling and high-confidence filtering to reduce pseudo-label noise and improve generalization. The system achieves an official dev score of 0.9712(micro-F1 0.9746, macro-F1 0.9745) and improves the test score from 0.46 to 0.73, ranking 84th out of 221 submissions."
}