@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goyal-etal-2026-paradise">
<titleInfo>
<title>Paradise at SemEval-2026 Task 12: Leveraging Instruction-Tuned Large Language Models with Chain-of-Thought Prompting for Abductive Event Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dhruv</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ishita</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jatin</namePart>
<namePart type="family">Bedi</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 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.</abstract>
<identifier type="citekey">goyal-etal-2026-paradise</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.100/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>706</start>
<end>712</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Paradise at SemEval-2026 Task 12: Leveraging Instruction-Tuned Large Language Models with Chain-of-Thought Prompting for Abductive Event Reasoning
%A Goyal, Dhruv
%A Gupta, Ishita
%A Bedi, Jatin
%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 goyal-etal-2026-paradise
%X 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.
%U https://aclanthology.org/2026.semeval-1.100/
%P 706-712
Markdown (Informal)
[Paradise at SemEval-2026 Task 12: Leveraging Instruction-Tuned Large Language Models with Chain-of-Thought Prompting for Abductive Event Reasoning](https://aclanthology.org/2026.semeval-1.100/) (Goyal et al., SemEval 2026)
ACL