@inproceedings{dai-lin-2026-alps,
title = "{ALPS}-Lab at {S}em{E}val-2026 Task 3: A Multilingual Generative {LLM} Approach for Dimensional Aspect Sentiment Analysis",
author = "Dai, Songqian and
Lin, 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-1.212/",
pages = "1652--1658",
ISBN = "979-8-89176-414-9",
abstract = "We propose a SFT approach for the DimABSA shared task, which predicts aspect-level sentiment intensities using large language models. The approach uses Gemma-3 27B with QLoRA for efficient fine-tuning on multilingual datasets. Merging data across languages improves performance, especially in low-resource domains. Post-processing removes duplicate outputs for accurate evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dai-lin-2026-alps">
<titleInfo>
<title>ALPS-Lab at SemEval-2026 Task 3: A Multilingual Generative LLM Approach for Dimensional Aspect Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Songqian</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lin</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 propose a SFT approach for the DimABSA shared task, which predicts aspect-level sentiment intensities using large language models. The approach uses Gemma-3 27B with QLoRA for efficient fine-tuning on multilingual datasets. Merging data across languages improves performance, especially in low-resource domains. Post-processing removes duplicate outputs for accurate evaluation.</abstract>
<identifier type="citekey">dai-lin-2026-alps</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.212/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1652</start>
<end>1658</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ALPS-Lab at SemEval-2026 Task 3: A Multilingual Generative LLM Approach for Dimensional Aspect Sentiment Analysis
%A Dai, Songqian
%A Lin, 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 dai-lin-2026-alps
%X We propose a SFT approach for the DimABSA shared task, which predicts aspect-level sentiment intensities using large language models. The approach uses Gemma-3 27B with QLoRA for efficient fine-tuning on multilingual datasets. Merging data across languages improves performance, especially in low-resource domains. Post-processing removes duplicate outputs for accurate evaluation.
%U https://aclanthology.org/2026.semeval-1.212/
%P 1652-1658
Markdown (Informal)
[ALPS-Lab at SemEval-2026 Task 3: A Multilingual Generative LLM Approach for Dimensional Aspect Sentiment Analysis](https://aclanthology.org/2026.semeval-1.212/) (Dai & Lin, SemEval 2026)
ACL