@inproceedings{gensale-etal-2025-bitsandbites,
title = "{B}its{A}nd{B}ites at {S}em{E}val-2025 Task 9: Improving Food Hazard Detection with Sequential Multitask Learning and Large Language Models",
author = "Gensale, Aurora and
Benedetto, Irene and
Gioacchini, Luca and
Cagliero, Luca and
Bosca, Alessio",
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-1.99/",
pages = "718--725",
ISBN = "979-8-89176-273-2",
abstract = "Automatic and early detection of foodborne hazards is crucial for preventing outbreaks. Existing AI-based solutions often struggle with the complexity and noise of food recall reports and overcome the dependency between product and hazard labels. We introduce a methodology to classify reports on food-related incidents to address these challenges. Our approach leverages LLM-based information extraction to minimize report variability, alongside a two-stage classification pipeline. The first model assigns coarse-grained labels, narrowing the space of eligible fine-grained labels for the second model. This sequential process allows us to capture hierarchical label dependencies between products and hazards and their respective categories. Additionally, we design each model with two classification heads relying on the inherent relations between food products and associated hazards. We validate our approach on two multi-label classification sub-tasks. Experimental results demonstrate the effectiveness of our approach, achieving an improvement of +30{\%} and +40{\%} in classification performance compared to the baseline."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gensale-etal-2025-bitsandbites">
<titleInfo>
<title>BitsAndBites at SemEval-2025 Task 9: Improving Food Hazard Detection with Sequential Multitask Learning and Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurora</namePart>
<namePart type="family">Gensale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irene</namePart>
<namePart type="family">Benedetto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Gioacchini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luca</namePart>
<namePart type="family">Cagliero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessio</namePart>
<namePart type="family">Bosca</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>Automatic and early detection of foodborne hazards is crucial for preventing outbreaks. Existing AI-based solutions often struggle with the complexity and noise of food recall reports and overcome the dependency between product and hazard labels. We introduce a methodology to classify reports on food-related incidents to address these challenges. Our approach leverages LLM-based information extraction to minimize report variability, alongside a two-stage classification pipeline. The first model assigns coarse-grained labels, narrowing the space of eligible fine-grained labels for the second model. This sequential process allows us to capture hierarchical label dependencies between products and hazards and their respective categories. Additionally, we design each model with two classification heads relying on the inherent relations between food products and associated hazards. We validate our approach on two multi-label classification sub-tasks. Experimental results demonstrate the effectiveness of our approach, achieving an improvement of +30% and +40% in classification performance compared to the baseline.</abstract>
<identifier type="citekey">gensale-etal-2025-bitsandbites</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.99/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>718</start>
<end>725</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BitsAndBites at SemEval-2025 Task 9: Improving Food Hazard Detection with Sequential Multitask Learning and Large Language Models
%A Gensale, Aurora
%A Benedetto, Irene
%A Gioacchini, Luca
%A Cagliero, Luca
%A Bosca, Alessio
%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 gensale-etal-2025-bitsandbites
%X Automatic and early detection of foodborne hazards is crucial for preventing outbreaks. Existing AI-based solutions often struggle with the complexity and noise of food recall reports and overcome the dependency between product and hazard labels. We introduce a methodology to classify reports on food-related incidents to address these challenges. Our approach leverages LLM-based information extraction to minimize report variability, alongside a two-stage classification pipeline. The first model assigns coarse-grained labels, narrowing the space of eligible fine-grained labels for the second model. This sequential process allows us to capture hierarchical label dependencies between products and hazards and their respective categories. Additionally, we design each model with two classification heads relying on the inherent relations between food products and associated hazards. We validate our approach on two multi-label classification sub-tasks. Experimental results demonstrate the effectiveness of our approach, achieving an improvement of +30% and +40% in classification performance compared to the baseline.
%U https://aclanthology.org/2025.semeval-1.99/
%P 718-725
Markdown (Informal)
[BitsAndBites at SemEval-2025 Task 9: Improving Food Hazard Detection with Sequential Multitask Learning and Large Language Models](https://aclanthology.org/2025.semeval-1.99/) (Gensale et al., SemEval 2025)
ACL