<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-2026-pali">
    <titleInfo>
        <title>PALI at SemEval-2026 Task 3: LoRA Fine-Tuning with Validation for DimABSA</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Cheng</namePart>
        <namePart type="family">Chen</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 describe the PALI system submitted to SemEval-2026 Task~3 (Dimensional Aspect-Based Sentiment Analysis), which requires predicting valence–arousal (VA) scores and extracting structured sentiment tuples across multiple languages.Our final system centers on LoRA fine-tuning of Qwen3-32B using Llama-Factory, together with data conversion/cleaning, multilingual data-mixing strategies, and inference-time validation and repair.We additionally explored retrieval-based few-shot prompting with BGE-M3, but found it less effective for learning consistent VA scoring preferences.On Track~A, our final system uses per-language LoRA adapters that mix all subtasks per language for a better trade-off between performance and efficiency.On the official test set, we achieve average per-language scores of 1.2071 RMSE\textbackslashVA for Subtask~1 and 0.5641/0.4905 cF1 for Subtask~2/3.On the development set, we find that per-language-per-task adapters further improve extraction cF1 but are less attractive in terms of training and deployment cost.For Track~B, we report results for VA prediction on five languages and two domains.</abstract>
    <identifier type="citekey">chen-2026-pali</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.93/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>641</start>
            <end>649</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PALI at SemEval-2026 Task 3: LoRA Fine-Tuning with Validation for DimABSA
%A Chen, Cheng
%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 chen-2026-pali
%X We describe the PALI system submitted to SemEval-2026 Task~3 (Dimensional Aspect-Based Sentiment Analysis), which requires predicting valence–arousal (VA) scores and extracting structured sentiment tuples across multiple languages.Our final system centers on LoRA fine-tuning of Qwen3-32B using Llama-Factory, together with data conversion/cleaning, multilingual data-mixing strategies, and inference-time validation and repair.We additionally explored retrieval-based few-shot prompting with BGE-M3, but found it less effective for learning consistent VA scoring preferences.On Track~A, our final system uses per-language LoRA adapters that mix all subtasks per language for a better trade-off between performance and efficiency.On the official test set, we achieve average per-language scores of 1.2071 RMSE\textbackslashVA for Subtask~1 and 0.5641/0.4905 cF1 for Subtask~2/3.On the development set, we find that per-language-per-task adapters further improve extraction cF1 but are less attractive in terms of training and deployment cost.For Track~B, we report results for VA prediction on five languages and two domains.
%U https://aclanthology.org/2026.semeval-1.93/
%P 641-649

Markdown (Informal)

[PALI at SemEval-2026 Task 3: LoRA Fine-Tuning with Validation for DimABSA](https://aclanthology.org/2026.semeval-1.93/) (Chen, SemEval 2026)

• PALI at SemEval-2026 Task 3: LoRA Fine-Tuning with Validation for DimABSA (Chen, SemEval 2026)

ACL

• Cheng Chen. 2026. PALI at SemEval-2026 Task 3: LoRA Fine-Tuning with Validation for DimABSA. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 641–649, San Diego, California, USA. Association for Computational Linguistics.