@inproceedings{yam-yam-2026-yam,
title = "Yam at {S}em{E}val-2026 Task 4: Failure-Driven Prompt Evolution for Narrative Comparison",
author = "Yam, Yen Yee and
Yam, Hong Meng",
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-1.421/",
pages = "3394--3398",
ISBN = "979-8-89176-414-9",
abstract = "We present a structured, parameter-free system for SemEval-2026 Task 4 on Narrative Story Similarity. Instead of treating similarity as scalar embedding proximity, we align model reasoning with the task ontology by decomposing each story into abstract theme, course of action, and outcome, and performing contrastive comparison over these dimensions. Our primary contribution is a closed-loop, failure-driven prompt optimization procedure that iteratively refines concise guideline documents while keeping model parameters fixed and reverting updates that degrade performance, thereby isolating improvements attributable to structured reasoning rather than representation learning. Ontology-aligned decomposition alone achieves 70{\%} accuracy on both train and test sets; with controlled guideline evolution, performance improves to 76{\%} on train and 73{\%} on test without additional supervision or fine-tuning. These results demonstrate that structured prompt optimization can meaningfully enhance contrastive narrative reasoning in a fully parameter-free setting."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yam-yam-2026-yam">
<titleInfo>
<title>Yam at SemEval-2026 Task 4: Failure-Driven Prompt Evolution for Narrative Comparison</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yen</namePart>
<namePart type="given">Yee</namePart>
<namePart type="family">Yam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hong</namePart>
<namePart type="given">Meng</namePart>
<namePart type="family">Yam</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 a structured, parameter-free system for SemEval-2026 Task 4 on Narrative Story Similarity. Instead of treating similarity as scalar embedding proximity, we align model reasoning with the task ontology by decomposing each story into abstract theme, course of action, and outcome, and performing contrastive comparison over these dimensions. Our primary contribution is a closed-loop, failure-driven prompt optimization procedure that iteratively refines concise guideline documents while keeping model parameters fixed and reverting updates that degrade performance, thereby isolating improvements attributable to structured reasoning rather than representation learning. Ontology-aligned decomposition alone achieves 70% accuracy on both train and test sets; with controlled guideline evolution, performance improves to 76% on train and 73% on test without additional supervision or fine-tuning. These results demonstrate that structured prompt optimization can meaningfully enhance contrastive narrative reasoning in a fully parameter-free setting.</abstract>
<identifier type="citekey">yam-yam-2026-yam</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.421/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3394</start>
<end>3398</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Yam at SemEval-2026 Task 4: Failure-Driven Prompt Evolution for Narrative Comparison
%A Yam, Yen Yee
%A Yam, Hong Meng
%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 yam-yam-2026-yam
%X We present a structured, parameter-free system for SemEval-2026 Task 4 on Narrative Story Similarity. Instead of treating similarity as scalar embedding proximity, we align model reasoning with the task ontology by decomposing each story into abstract theme, course of action, and outcome, and performing contrastive comparison over these dimensions. Our primary contribution is a closed-loop, failure-driven prompt optimization procedure that iteratively refines concise guideline documents while keeping model parameters fixed and reverting updates that degrade performance, thereby isolating improvements attributable to structured reasoning rather than representation learning. Ontology-aligned decomposition alone achieves 70% accuracy on both train and test sets; with controlled guideline evolution, performance improves to 76% on train and 73% on test without additional supervision or fine-tuning. These results demonstrate that structured prompt optimization can meaningfully enhance contrastive narrative reasoning in a fully parameter-free setting.
%U https://aclanthology.org/2026.semeval-1.421/
%P 3394-3398
Markdown (Informal)
[Yam at SemEval-2026 Task 4: Failure-Driven Prompt Evolution for Narrative Comparison](https://aclanthology.org/2026.semeval-1.421/) (Yam & Yam, SemEval 2026)
ACL