@inproceedings{li-yang-2026-hllwan,
title = "hllwan at {S}em{E}val-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis via {LLM} Feature Fusion and Test-Time Adaptation",
author = "Li, Jinglong and
Yang, Yang",
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-1.157/",
pages = "1147--1152",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes the system developed bythe team for SemEval-2026 Task 3: Di-mensional Aspect-Based Sentiment Analysis(DimABSA). Unlike traditional categorical sen-timent analysis, predicting continuous Valenceand Arousal (VA) scores across multiple lan-guages and domains poses significant theoret-ical and engineering challenges. To systemat-ically address data scarcity and cross-domaindistribution shifts, we propose a highly robustframework. First, we implement a translation-based data augmentation strategy with preciseHTML-tag alignment to mitigate low-resourceconstraints. Second, we introduce an unsuper-vised opinion extraction module based on syn-tactic dependency parsing to explicitly capturesentiment-bearing words. Third, we designa Tripartite Feature Fusion architecture builtupon both encoder-only (DeBERTa-v3) andcausal LLM (Qwen2.5) models to dynamicallyaggregate global and localized aspect-opinionembeddings. Finally, we apply an unsupervisedTest-Time Adaptation (TTA) mechanism to cal-ibrate normalization layers on the fly. Our sys-tem demonstrates highly competitive perfor-mance while offering critical insights into thelimitations of LLMs in cross-lingual sentimenttransfer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-yang-2026-hllwan">
<titleInfo>
<title>hllwan at SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis via LLM Feature Fusion and Test-Time Adaptation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinglong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Yang</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 system developed bythe team for SemEval-2026 Task 3: Di-mensional Aspect-Based Sentiment Analysis(DimABSA). Unlike traditional categorical sen-timent analysis, predicting continuous Valenceand Arousal (VA) scores across multiple lan-guages and domains poses significant theoret-ical and engineering challenges. To systemat-ically address data scarcity and cross-domaindistribution shifts, we propose a highly robustframework. First, we implement a translation-based data augmentation strategy with preciseHTML-tag alignment to mitigate low-resourceconstraints. Second, we introduce an unsuper-vised opinion extraction module based on syn-tactic dependency parsing to explicitly capturesentiment-bearing words. Third, we designa Tripartite Feature Fusion architecture builtupon both encoder-only (DeBERTa-v3) andcausal LLM (Qwen2.5) models to dynamicallyaggregate global and localized aspect-opinionembeddings. Finally, we apply an unsupervisedTest-Time Adaptation (TTA) mechanism to cal-ibrate normalization layers on the fly. Our sys-tem demonstrates highly competitive perfor-mance while offering critical insights into thelimitations of LLMs in cross-lingual sentimenttransfer.</abstract>
<identifier type="citekey">li-yang-2026-hllwan</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.157/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1147</start>
<end>1152</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T hllwan at SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis via LLM Feature Fusion and Test-Time Adaptation
%A Li, Jinglong
%A Yang, Yang
%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 li-yang-2026-hllwan
%X This paper describes the system developed bythe team for SemEval-2026 Task 3: Di-mensional Aspect-Based Sentiment Analysis(DimABSA). Unlike traditional categorical sen-timent analysis, predicting continuous Valenceand Arousal (VA) scores across multiple lan-guages and domains poses significant theoret-ical and engineering challenges. To systemat-ically address data scarcity and cross-domaindistribution shifts, we propose a highly robustframework. First, we implement a translation-based data augmentation strategy with preciseHTML-tag alignment to mitigate low-resourceconstraints. Second, we introduce an unsuper-vised opinion extraction module based on syn-tactic dependency parsing to explicitly capturesentiment-bearing words. Third, we designa Tripartite Feature Fusion architecture builtupon both encoder-only (DeBERTa-v3) andcausal LLM (Qwen2.5) models to dynamicallyaggregate global and localized aspect-opinionembeddings. Finally, we apply an unsupervisedTest-Time Adaptation (TTA) mechanism to cal-ibrate normalization layers on the fly. Our sys-tem demonstrates highly competitive perfor-mance while offering critical insights into thelimitations of LLMs in cross-lingual sentimenttransfer.
%U https://aclanthology.org/2026.semeval-1.157/
%P 1147-1152
Markdown (Informal)
[hllwan at SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis via LLM Feature Fusion and Test-Time Adaptation](https://aclanthology.org/2026.semeval-1.157/) (Li & Yang, SemEval 2026)
ACL