@inproceedings{randl-etal-2025-semeval,
title = "{S}em{E}val-2025 Task 9: The Food Hazard Detection Challenge",
author = "Randl, Korbinian and
Pavlopoulos, John and
Henriksson, Aron and
Lindgren, Tony and
Bakagianni, Juli",
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.325/",
pages = "2523--2534",
ISBN = "979-8-89176-273-2",
abstract = "In this challenge, we explored text-based food hazard prediction with long tail distributed classes. The task was divided into two subtasks: (1) predicting whether a web text implies one of ten food-hazard categories and identifying the associated food category, and (2) providing a more fine-grained classification by assigning a specific label to both the hazard and the product. Our findings highlight that large language model-generated synthetic data can be highly effective for oversampling long-tail distributions. Furthermore, we find that fine-tuned encoder-only, encoder-decoder, and decoder-only systems achieve comparable maximum performance across both subtasks. During this challenge, we are gradually releasing (under CC BY-NC-SA 4.0) a novel set of 6,644 manually labeled food-incident reports."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="randl-etal-2025-semeval">
<titleInfo>
<title>SemEval-2025 Task 9: The Food Hazard Detection Challenge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Korbinian</namePart>
<namePart type="family">Randl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aron</namePart>
<namePart type="family">Henriksson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="family">Lindgren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juli</namePart>
<namePart type="family">Bakagianni</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 challenge, we explored text-based food hazard prediction with long tail distributed classes. The task was divided into two subtasks: (1) predicting whether a web text implies one of ten food-hazard categories and identifying the associated food category, and (2) providing a more fine-grained classification by assigning a specific label to both the hazard and the product. Our findings highlight that large language model-generated synthetic data can be highly effective for oversampling long-tail distributions. Furthermore, we find that fine-tuned encoder-only, encoder-decoder, and decoder-only systems achieve comparable maximum performance across both subtasks. During this challenge, we are gradually releasing (under CC BY-NC-SA 4.0) a novel set of 6,644 manually labeled food-incident reports.</abstract>
<identifier type="citekey">randl-etal-2025-semeval</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.325/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2523</start>
<end>2534</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemEval-2025 Task 9: The Food Hazard Detection Challenge
%A Randl, Korbinian
%A Pavlopoulos, John
%A Henriksson, Aron
%A Lindgren, Tony
%A Bakagianni, Juli
%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 randl-etal-2025-semeval
%X In this challenge, we explored text-based food hazard prediction with long tail distributed classes. The task was divided into two subtasks: (1) predicting whether a web text implies one of ten food-hazard categories and identifying the associated food category, and (2) providing a more fine-grained classification by assigning a specific label to both the hazard and the product. Our findings highlight that large language model-generated synthetic data can be highly effective for oversampling long-tail distributions. Furthermore, we find that fine-tuned encoder-only, encoder-decoder, and decoder-only systems achieve comparable maximum performance across both subtasks. During this challenge, we are gradually releasing (under CC BY-NC-SA 4.0) a novel set of 6,644 manually labeled food-incident reports.
%U https://aclanthology.org/2025.semeval-1.325/
%P 2523-2534
Markdown (Informal)
[SemEval-2025 Task 9: The Food Hazard Detection Challenge](https://aclanthology.org/2025.semeval-1.325/) (Randl et al., SemEval 2025)
ACL
- Korbinian Randl, John Pavlopoulos, Aron Henriksson, Tony Lindgren, and Juli Bakagianni. 2025. SemEval-2025 Task 9: The Food Hazard Detection Challenge. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2523–2534, Vienna, Austria. Association for Computational Linguistics.