PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores

Zhihao Ruan; Kaifeng Yang; Cheng Chen; Wenwen Dai; Wenjia Mao

PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores

Zhihao Ruan, Kaifeng Yang, Cheng Chen, Wenwen Dai, Wenjia Mao

Correct Metadata for

Use this form to create a GitHub issue with structured data describing the correction. You will need a GitHub account. Once you create that issue, the correction will be reviewed by a staff member.

⚠️ Mobile Users: Submitting this form to create a new issue will only work with github.com, not the GitHub Mobile app.

Important: The Anthology treat PDFs as authoritative. Please use this form only to correct data that is out of line with the PDF. See our corrections guidelines if you need to change the PDF.

Title Adjust the title. Retain tags such as <fixed-case>.

Authors Adjust author names and order to match the PDF.

Abstract Correct abstract if needed. Retain XML formatting tags such as <tex-math>. You may use <b>...</b> for bold, <i>...</i> for italic, and <url>...</url> for URLs.

Verification against PDF Ensure that the new title/authors match the snapshot below. (If there is no snapshot or it is too small, consult the PDF.)

Authors concatenated from the text boxes above:

ALL author names match the snapshot above—including middle initials, hyphens, and accents.

Abstract

To address the valence and arousal score prediction task in Dimensional Aspect-Based Sentiment Analysis (DimABSA), we propose a two-stage strategy. In the first stage, we conduct post-training on a Large Language Model (LLM) via a Supervised Fine-Tuning (SFT) scheme, followed by generating initial predictions for valence and arousal scores. In the second stage, we perform distribution adaptation on the initial results by leveraging the training set distribution through various techniques, including Gaussian distribution modeling, quantile mapping, and the Sinkhorn algorithm.

Anthology ID:: 2026.semeval-1.193
Volume:: Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
Month:: July
Year:: 2026
Address:: San Diego, California, USA
Editors:: Ekaterina Kochmar, Debanjan Ghosh, Kai North, Mamoru Komachi
Venues:: SemEval | WS
SIG:
Publisher:: Association for Computational Linguistics
Note:
Pages:: 1489–1494
Language:
URL:: https://aclanthology.org/2026.semeval-1.193/
DOI:
Bibkey:
Cite (ACL):: Zhihao Ruan, Kaifeng Yang, Cheng Chen, Wenwen Dai, and Wenjia Mao. 2026. PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1489–1494, San Diego, California, USA. Association for Computational Linguistics.
Cite (Informal):: PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores (Ruan et al., SemEval 2026)
Copy Citation:
PDF:: https://aclanthology.org/2026.semeval-1.193.pdf

PDF Cite Search Fix data

Export citation

BibTeX
MODS XML
Endnote
Preformatted

@inproceedings{ruan-etal-2026-pai,
    title = "{PAI} at {S}em{E}val-2026 Task 3: An {LLM} and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores",
    author = "Ruan, Zhihao  and
      Yang, Kaifeng  and
      Chen, Cheng  and
      Dai, Wenwen  and
      Mao, Wenjia",
    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-1.193/",
    pages = "1489--1494",
    ISBN = "979-8-89176-414-9",
    abstract = "To address the valence and arousal score prediction task in Dimensional Aspect-Based Sentiment Analysis (DimABSA), we propose a two-stage strategy. In the first stage, we conduct post-training on a Large Language Model (LLM) via a Supervised Fine-Tuning (SFT) scheme, followed by generating initial predictions for valence and arousal scores. In the second stage, we perform distribution adaptation on the initial results by leveraging the training set distribution through various techniques, including Gaussian distribution modeling, quantile mapping, and the Sinkhorn algorithm."
}

Download as File

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruan-etal-2026-pai">
    <titleInfo>
        <title>PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhihao</namePart>
        <namePart type="family">Ruan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kaifeng</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cheng</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenwen</namePart>
        <namePart type="family">Dai</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wenjia</namePart>
        <namePart type="family">Mao</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>To address the valence and arousal score prediction task in Dimensional Aspect-Based Sentiment Analysis (DimABSA), we propose a two-stage strategy. In the first stage, we conduct post-training on a Large Language Model (LLM) via a Supervised Fine-Tuning (SFT) scheme, followed by generating initial predictions for valence and arousal scores. In the second stage, we perform distribution adaptation on the initial results by leveraging the training set distribution through various techniques, including Gaussian distribution modeling, quantile mapping, and the Sinkhorn algorithm.</abstract>
    <identifier type="citekey">ruan-etal-2026-pai</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.193/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>1489</start>
            <end>1494</end>
        </extent>
    </part>
</mods>
</modsCollection>

Download as File

%0 Conference Proceedings
%T PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores
%A Ruan, Zhihao
%A Yang, Kaifeng
%A Chen, Cheng
%A Dai, Wenwen
%A Mao, Wenjia
%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 ruan-etal-2026-pai
%X To address the valence and arousal score prediction task in Dimensional Aspect-Based Sentiment Analysis (DimABSA), we propose a two-stage strategy. In the first stage, we conduct post-training on a Large Language Model (LLM) via a Supervised Fine-Tuning (SFT) scheme, followed by generating initial predictions for valence and arousal scores. In the second stage, we perform distribution adaptation on the initial results by leveraging the training set distribution through various techniques, including Gaussian distribution modeling, quantile mapping, and the Sinkhorn algorithm.
%U https://aclanthology.org/2026.semeval-1.193/
%P 1489-1494

Download as File

Markdown (Informal)

[PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores](https://aclanthology.org/2026.semeval-1.193/) (Ruan et al., SemEval 2026)

PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores (Ruan et al., SemEval 2026)

ACL

Zhihao Ruan, Kaifeng Yang, Cheng Chen, Wenwen Dai, and Wenjia Mao. 2026. PAI at SemEval-2026 Task 3: An LLM and Data Redistribution Adaptation-Based Predictive Strategy for Valence-Arousal Scores. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1489–1494, San Diego, California, USA. Association for Computational Linguistics.