YNU-HPCC at SemEval-2026 Task 12: Retrieval-Guided Reasoning with Teacher Distillation for Abductive Event Reasoning
Year: 2026
Type: conference-paper
Abstract: This paper describes the YNU-HPCC system for SemEval-2026 Task 12, Abductive Event Reasoning (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 boundarysensitive set-level evaluation.This paper proposes a two-stage framework.Stage 1 trains a DeBERTa-v3-base student with retrievalguided 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 pseudolabel 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.
Authors: Yuwei Sun, Jin Wang, Xuejie Zhang
Institution: Yunnan University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: 基于多维度连续情感空间的文本生成技术研究, G5917579187
OpenAlex ID: W7166850643