@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-ynu">
<titleInfo>
<title>YNU-HPCC at SemEval-2026 Task 12: Retrieval-Guided Reasoning with Teacher Distillation for Abductive Event Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuwei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuejie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">sun-etal-2026-ynu</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.30/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>206</start>
<end>212</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YNU-HPCC at SemEval-2026 Task 12: Retrieval-Guided Reasoning with Teacher Distillation for Abductive Event Reasoning
%A Sun, Yuwei
%A Wang, Jin
%A Zhang, Xuejie
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F sun-etal-2026-ynu
%X 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.
%U https://aclanthology.org/2026.semeval-1.30/
%P 206-212
Markdown (Informal)
[YNU-HPCC at SemEval-2026 Task 12: Retrieval-Guided Reasoning with Teacher Distillation for Abductive Event Reasoning](https://aclanthology.org/2026.semeval-1.30/) (Sun et al., SemEval 2026)
ACL