@inproceedings{wan-etal-2025-pateam,
title = "{PAT}eam at {S}em{E}val-2025 Task 9: {LLM}-Augmented Fusion for {AI}-Driven Food Safety Hazard Detection",
author = "Wan, Xue and
Su, Fengping and
Sun, Ling and
Lin, Yuyang and
Chen, Pengfei",
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-1.249/",
pages = "1912--1918",
ISBN = "979-8-89176-273-2",
abstract = "This paper introduces the approach we adopted for the SemEval-2025 ``Food Hazard Detection'' task, which aims to predict coarse-grained categories (such as ``product category'' and ``hazard category'') and fine-grained vectors (such as specific products like ``ice cream'' or hazards like ``salmonella'') from noisy, long-tailed text data.To address the issues of dirty data, as well as the severe long-tail distribution of text labels and length in the data, we proposed a pipeline system. This system combines data cleaning, LLM-based enhancement, label resampling, and ensemble learning to tackle data sparsity and label imbalance problems.The two subtasks have strong semantic relatedness. By integrating them into a unified multiturn dialogue framework, we fine-tuned five models using a bagging approach. Ultimately, we achieved good results in both subtasks, ranking 5th (with an F1 score of 80.17{\%} for ST1 and 52.66{\%} for ST2)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wan-etal-2025-pateam">
<titleInfo>
<title>PATeam at SemEval-2025 Task 9: LLM-Augmented Fusion for AI-Driven Food Safety Hazard Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xue</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fengping</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ling</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyang</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Chen</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>This paper introduces the approach we adopted for the SemEval-2025 “Food Hazard Detection” task, which aims to predict coarse-grained categories (such as “product category” and “hazard category”) and fine-grained vectors (such as specific products like “ice cream” or hazards like “salmonella”) from noisy, long-tailed text data.To address the issues of dirty data, as well as the severe long-tail distribution of text labels and length in the data, we proposed a pipeline system. This system combines data cleaning, LLM-based enhancement, label resampling, and ensemble learning to tackle data sparsity and label imbalance problems.The two subtasks have strong semantic relatedness. By integrating them into a unified multiturn dialogue framework, we fine-tuned five models using a bagging approach. Ultimately, we achieved good results in both subtasks, ranking 5th (with an F1 score of 80.17% for ST1 and 52.66% for ST2).</abstract>
<identifier type="citekey">wan-etal-2025-pateam</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.249/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1912</start>
<end>1918</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PATeam at SemEval-2025 Task 9: LLM-Augmented Fusion for AI-Driven Food Safety Hazard Detection
%A Wan, Xue
%A Su, Fengping
%A Sun, Ling
%A Lin, Yuyang
%A Chen, Pengfei
%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 wan-etal-2025-pateam
%X This paper introduces the approach we adopted for the SemEval-2025 “Food Hazard Detection” task, which aims to predict coarse-grained categories (such as “product category” and “hazard category”) and fine-grained vectors (such as specific products like “ice cream” or hazards like “salmonella”) from noisy, long-tailed text data.To address the issues of dirty data, as well as the severe long-tail distribution of text labels and length in the data, we proposed a pipeline system. This system combines data cleaning, LLM-based enhancement, label resampling, and ensemble learning to tackle data sparsity and label imbalance problems.The two subtasks have strong semantic relatedness. By integrating them into a unified multiturn dialogue framework, we fine-tuned five models using a bagging approach. Ultimately, we achieved good results in both subtasks, ranking 5th (with an F1 score of 80.17% for ST1 and 52.66% for ST2).
%U https://aclanthology.org/2025.semeval-1.249/
%P 1912-1918
Markdown (Informal)
[PATeam at SemEval-2025 Task 9: LLM-Augmented Fusion for AI-Driven Food Safety Hazard Detection](https://aclanthology.org/2025.semeval-1.249/) (Wan et al., SemEval 2025)
ACL