@inproceedings{guo-etal-2026-narrative,
title = "Narrative Nexus at {S}em{E}val-2026 Task 4: Modeling Narrative Similarity via Instruction-Based Fine-Tuning and Synthetic Data Augmentation",
author = "Guo, Haotan and
Na, Hongbin and
Wang, Zimu and
Wang, Wei",
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-1.352/",
pages = "2793--2799",
ISBN = "979-8-89176-414-9",
abstract = "Narrative similarity assessment requires models to reason beyond surface-level lexical overlap and capture higher-level plot structures and thematic relationships. In this paper, we address SemEval-2026 Task 4 Track A: Narrative Story Similarity by reformulating it as an instruction-following generation problem. We employ parameter-efficient fine-tuning via LoRA to adapt pretrained large language models for triplet-based narrative comparison. To overcome the limitations imposed by the scarcity of human-annotated data, we further incorporate synthetic triplet samples generated by a large language model for data augmentation. Experimental results demonstrate that our fine-tuned Qwen2.5-7B model achieves competitive performance, outperforming the zero-shot GPT-4o-mini baseline. These findings underscore the effectiveness of task-specific adaptation combined with synthetic data augmentation for narrative similarity modeling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2026-narrative">
<titleInfo>
<title>Narrative Nexus at SemEval-2026 Task 4: Modeling Narrative Similarity via Instruction-Based Fine-Tuning and Synthetic Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haotan</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongbin</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Wang</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>Narrative similarity assessment requires models to reason beyond surface-level lexical overlap and capture higher-level plot structures and thematic relationships. In this paper, we address SemEval-2026 Task 4 Track A: Narrative Story Similarity by reformulating it as an instruction-following generation problem. We employ parameter-efficient fine-tuning via LoRA to adapt pretrained large language models for triplet-based narrative comparison. To overcome the limitations imposed by the scarcity of human-annotated data, we further incorporate synthetic triplet samples generated by a large language model for data augmentation. Experimental results demonstrate that our fine-tuned Qwen2.5-7B model achieves competitive performance, outperforming the zero-shot GPT-4o-mini baseline. These findings underscore the effectiveness of task-specific adaptation combined with synthetic data augmentation for narrative similarity modeling.</abstract>
<identifier type="citekey">guo-etal-2026-narrative</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.352/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2793</start>
<end>2799</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Narrative Nexus at SemEval-2026 Task 4: Modeling Narrative Similarity via Instruction-Based Fine-Tuning and Synthetic Data Augmentation
%A Guo, Haotan
%A Na, Hongbin
%A Wang, Zimu
%A Wang, Wei
%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 guo-etal-2026-narrative
%X Narrative similarity assessment requires models to reason beyond surface-level lexical overlap and capture higher-level plot structures and thematic relationships. In this paper, we address SemEval-2026 Task 4 Track A: Narrative Story Similarity by reformulating it as an instruction-following generation problem. We employ parameter-efficient fine-tuning via LoRA to adapt pretrained large language models for triplet-based narrative comparison. To overcome the limitations imposed by the scarcity of human-annotated data, we further incorporate synthetic triplet samples generated by a large language model for data augmentation. Experimental results demonstrate that our fine-tuned Qwen2.5-7B model achieves competitive performance, outperforming the zero-shot GPT-4o-mini baseline. These findings underscore the effectiveness of task-specific adaptation combined with synthetic data augmentation for narrative similarity modeling.
%U https://aclanthology.org/2026.semeval-1.352/
%P 2793-2799
Markdown (Informal)
[Narrative Nexus at SemEval-2026 Task 4: Modeling Narrative Similarity via Instruction-Based Fine-Tuning and Synthetic Data Augmentation](https://aclanthology.org/2026.semeval-1.352/) (Guo et al., SemEval 2026)
ACL