@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prasad-etal-2026-clutch">
<titleInfo>
<title>Clutch or Cry at SemEval-2026 Task 12: Offline Retrieval-Augmented Generation with Frozen DeBERTa for Abductive Event Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aayush</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudra</namePart>
<namePart type="family">Trivedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arshad</namePart>
<namePart type="family">Khatib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrikant</namePart>
<namePart type="family">Malviya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naveen</namePart>
<namePart type="family">Kumar</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>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.</abstract>
<identifier type="citekey">prasad-etal-2026-clutch</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.261/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2078</start>
<end>2081</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clutch or Cry at SemEval-2026 Task 12: Offline Retrieval-Augmented Generation with Frozen DeBERTa for Abductive Event Reasoning
%A Prasad, Aayush
%A Trivedi, Rudra
%A Khatib, Arshad
%A Malviya, Shrikant
%A Kumar, Naveen
%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 prasad-etal-2026-clutch
%X 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.
%U https://aclanthology.org/2026.semeval-1.261/
%P 2078-2081
Markdown (Informal)
[Clutch or Cry at SemEval-2026 Task 12: Offline Retrieval-Augmented Generation with Frozen DeBERTa for Abductive Event Reasoning](https://aclanthology.org/2026.semeval-1.261/) (Prasad et al., SemEval 2026)
ACL