@inproceedings{hong-etal-2025-ncl,
title = "{NCL}-{U}o{R} at {S}em{E}val-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified {R}ef{C}hecker and Modified {S}efl{C}heck{GPT}",
author = "Hong, Jiaying and
Markchom, Thanet and
Xu, Jianfei and
Wu, Tong and
Liang, Huizhi",
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-1.39/",
pages = "271--279",
ISBN = "979-8-89176-273-2",
abstract = "SemEval-2025 Task 3 (Mu-SHROOM) focuses on detecting hallucinations in content generated by various large language models (LLMs) across multiple languages. This task involves not only identifying the presence of hallucinations but also pinpointing their specific occurrences. To tackle this challenge, this study introduces two methods: modified RefChecker and modified SelfCheckGPT. The modified RefChecker integrates prompt-based factual verification into References, structuring them as claim-based tests rather than single external knowledge sources. The modified SelfCheckGPT {\textasciitilde}incorporates external knowledge to overcome its reliance on internal knowledge. In addition, both methods' original prompt designs are enhanced to identify hallucinated words within LLM-generated texts. Experimental results demonstrate the effectiveness of the approach, achieving a high ranking on the test dataset in detecting hallucinations across various languages, with an average IoU of 0.5310 and an average COR of 0.5669."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hong-etal-2025-ncl">
<titleInfo>
<title>NCL-UoR at SemEval-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified RefChecker and Modified SeflCheckGPT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaying</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanet</namePart>
<namePart type="family">Markchom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huizhi</namePart>
<namePart type="family">Liang</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>SemEval-2025 Task 3 (Mu-SHROOM) focuses on detecting hallucinations in content generated by various large language models (LLMs) across multiple languages. This task involves not only identifying the presence of hallucinations but also pinpointing their specific occurrences. To tackle this challenge, this study introduces two methods: modified RefChecker and modified SelfCheckGPT. The modified RefChecker integrates prompt-based factual verification into References, structuring them as claim-based tests rather than single external knowledge sources. The modified SelfCheckGPT ~incorporates external knowledge to overcome its reliance on internal knowledge. In addition, both methods’ original prompt designs are enhanced to identify hallucinated words within LLM-generated texts. Experimental results demonstrate the effectiveness of the approach, achieving a high ranking on the test dataset in detecting hallucinations across various languages, with an average IoU of 0.5310 and an average COR of 0.5669.</abstract>
<identifier type="citekey">hong-etal-2025-ncl</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.39/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>271</start>
<end>279</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NCL-UoR at SemEval-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified RefChecker and Modified SeflCheckGPT
%A Hong, Jiaying
%A Markchom, Thanet
%A Xu, Jianfei
%A Wu, Tong
%A Liang, Huizhi
%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 hong-etal-2025-ncl
%X SemEval-2025 Task 3 (Mu-SHROOM) focuses on detecting hallucinations in content generated by various large language models (LLMs) across multiple languages. This task involves not only identifying the presence of hallucinations but also pinpointing their specific occurrences. To tackle this challenge, this study introduces two methods: modified RefChecker and modified SelfCheckGPT. The modified RefChecker integrates prompt-based factual verification into References, structuring them as claim-based tests rather than single external knowledge sources. The modified SelfCheckGPT ~incorporates external knowledge to overcome its reliance on internal knowledge. In addition, both methods’ original prompt designs are enhanced to identify hallucinated words within LLM-generated texts. Experimental results demonstrate the effectiveness of the approach, achieving a high ranking on the test dataset in detecting hallucinations across various languages, with an average IoU of 0.5310 and an average COR of 0.5669.
%U https://aclanthology.org/2025.semeval-1.39/
%P 271-279
Markdown (Informal)
[NCL-UoR at SemEval-2025 Task 3: Detecting Multilingual Hallucination and Related Observable Overgeneration Text Spans with Modified RefChecker and Modified SeflCheckGPT](https://aclanthology.org/2025.semeval-1.39/) (Hong et al., SemEval 2025)
ACL