<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="phu-thin-2026-stochastic">
    <titleInfo>
        <title>Stochastic Gradient Descenders at SemEval-2026 Task 9: Few-Shot LLM Prompting for Polarization Type Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Huynh</namePart>
        <namePart type="family">Phu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dang</namePart>
        <namePart type="family">Thin</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 presents our system for SemEval-2026 Task~9 (POLAR), Subtask~2, which focuses on classifying polarization types in social media text. We investigate three paradigms: (i) fine-tuning mDeBERTa-v3 with domain-adaptive pre-training, (ii) parameter-efficient adaptation of Qwen2.5-32B using LoRA, and (iii) few-shot prompting with Llama-3.3-70B-Instruct. Experimental results show that few-shot prompting, despite requiring no task-specific training, outperforms both fine-tuning and parameter-efficient approaches. Notably, it achieves non-zero F1 scores across all polarization categories, which is critical under macro-averaged evaluation. Our system ranks 2nd out of 29 English submissions on the official leaderboard, achieving an F1 Macro of 0.5157. These findings highlight the effectiveness of large instruction-tuned models in low-resource, label-imbalanced classification settings.</abstract>
    <identifier type="citekey">phu-thin-2026-stochastic</identifier>
    <location>
        <url>https://aclanthology.org/2026.semeval-1.129/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>938</start>
            <end>942</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Stochastic Gradient Descenders at SemEval-2026 Task 9: Few-Shot LLM Prompting for Polarization Type Classification
%A Phu, Huynh
%A Thin, Dang
%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 phu-thin-2026-stochastic
%X This paper presents our system for SemEval-2026 Task~9 (POLAR), Subtask~2, which focuses on classifying polarization types in social media text. We investigate three paradigms: (i) fine-tuning mDeBERTa-v3 with domain-adaptive pre-training, (ii) parameter-efficient adaptation of Qwen2.5-32B using LoRA, and (iii) few-shot prompting with Llama-3.3-70B-Instruct. Experimental results show that few-shot prompting, despite requiring no task-specific training, outperforms both fine-tuning and parameter-efficient approaches. Notably, it achieves non-zero F1 scores across all polarization categories, which is critical under macro-averaged evaluation. Our system ranks 2nd out of 29 English submissions on the official leaderboard, achieving an F1 Macro of 0.5157. These findings highlight the effectiveness of large instruction-tuned models in low-resource, label-imbalanced classification settings.
%U https://aclanthology.org/2026.semeval-1.129/
%P 938-942

Markdown (Informal)

[Stochastic Gradient Descenders at SemEval-2026 Task 9: Few-Shot LLM Prompting for Polarization Type Classification](https://aclanthology.org/2026.semeval-1.129/) (Phu & Thin, SemEval 2026)

• Stochastic Gradient Descenders at SemEval-2026 Task 9: Few-Shot LLM Prompting for Polarization Type Classification (Phu & Thin, SemEval 2026)

ACL

• Huynh Phu and Dang Thin. 2026. Stochastic Gradient Descenders at SemEval-2026 Task 9: Few-Shot LLM Prompting for Polarization Type Classification. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 938–942, San Diego, California, USA. Association for Computational Linguistics.