<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spiewak-karas-2025-opi">
    <titleInfo>
        <title>OPI-DRO-HEL at SemEval-2025 Task 9: Integrating Transformer-Based Classification with LLM-Assisted Few-Shot Learning for Food Hazard Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Martyna</namePart>
        <namePart type="family">Śpiewak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daniel</namePart>
        <namePart type="family">Karaś</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Rosenthal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aiala</namePart>
            <namePart type="family">Rosá</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">Marcos</namePart>
            <namePart type="family">Zampieri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-273-2</identifier>
    </relatedItem>
    <abstract>In this paper, we propose a hybrid approach for food hazard detection that combines a fine-tuned RoBERTa classifier with few-shot learning using an LLM model (GPT-3.5-turbo). We address challenges related to unstructured text and class imbalance by applying class weighting and keyword extraction (KeyBERT, YAKE, and Sentence-BERT). When RoBERTa’s confidence falls below a given threshold, a structured prompt which comprising the title, extracted keywords, and a few representative examples is used to re-evaluate the prediction with ChatGPT.</abstract>
    <identifier type="citekey">spiewak-karas-2025-opi</identifier>
    <location>
        <url>https://aclanthology.org/2025.semeval-1.155/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>1174</start>
            <end>1180</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T OPI-DRO-HEL at SemEval-2025 Task 9: Integrating Transformer-Based Classification with LLM-Assisted Few-Shot Learning for Food Hazard Detection
%A Śpiewak, Martyna
%A Karaś, Daniel
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F spiewak-karas-2025-opi
%X In this paper, we propose a hybrid approach for food hazard detection that combines a fine-tuned RoBERTa classifier with few-shot learning using an LLM model (GPT-3.5-turbo). We address challenges related to unstructured text and class imbalance by applying class weighting and keyword extraction (KeyBERT, YAKE, and Sentence-BERT). When RoBERTa’s confidence falls below a given threshold, a structured prompt which comprising the title, extracted keywords, and a few representative examples is used to re-evaluate the prediction with ChatGPT.
%U https://aclanthology.org/2025.semeval-1.155/
%P 1174-1180

Markdown (Informal)

[OPI-DRO-HEL at SemEval-2025 Task 9: Integrating Transformer-Based Classification with LLM-Assisted Few-Shot Learning for Food Hazard Detection](https://aclanthology.org/2025.semeval-1.155/) (Śpiewak & Karaś, SemEval 2025)

• OPI-DRO-HEL at SemEval-2025 Task 9: Integrating Transformer-Based Classification with LLM-Assisted Few-Shot Learning for Food Hazard Detection (Śpiewak & Karaś, SemEval 2025)

ACL

• Martyna Śpiewak and Daniel Karaś. 2025. OPI-DRO-HEL at SemEval-2025 Task 9: Integrating Transformer-Based Classification with LLM-Assisted Few-Shot Learning for Food Hazard Detection. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 1174–1180, Vienna, Austria. Association for Computational Linguistics.