@inproceedings{tufa-etal-2025-firc-nlp,
title = "{F}i{RC}-{NLP} at {S}em{E}val-2025 Task 3: Exploring Prompting Approaches for Detecting Hallucinations in {LLM}s",
author = "Tufa, Wondimagegnhue and
Hassan, Fadi and
Collell, Guillem and
Tu, Dandan and
Tu, Yi and
Ni, Sang and
Tan, Kuan Eeik",
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-1.273/",
pages = "2096--2102",
ISBN = "979-8-89176-273-2",
abstract = "This paper presents a system description forthe SemEval Mu-SHROOM task, focusing ondetecting hallucination spans in the outputsof instruction-tuned Large Language Models(LLMs) across 14 languages. We comparetwo distinct approaches: Prompt-Based Ap-proach (PBA), which leverages the capabilityof LLMs to detect hallucination spans usingdifferent prompting strategies, and the Fine-Tuning-Based Approach (FBA), which fine-tunes pre-trained Language Models (LMs) toextract hallucination spans in a supervised man-ner. Our experiments reveal that PBA, espe-cially when incorporating explicit references orexternal knowledge, outperforms FBA. How-ever, the effectiveness of PBA varies across lan-guages, likely due to differences in languagerepresentation within LLMs"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tufa-etal-2025-firc-nlp">
<titleInfo>
<title>FiRC-NLP at SemEval-2025 Task 3: Exploring Prompting Approaches for Detecting Hallucinations in LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wondimagegnhue</namePart>
<namePart type="family">Tufa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fadi</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillem</namePart>
<namePart type="family">Collell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dandan</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sang</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuan</namePart>
<namePart type="given">Eeik</namePart>
<namePart type="family">Tan</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 presents a system description forthe SemEval Mu-SHROOM task, focusing ondetecting hallucination spans in the outputsof instruction-tuned Large Language Models(LLMs) across 14 languages. We comparetwo distinct approaches: Prompt-Based Ap-proach (PBA), which leverages the capabilityof LLMs to detect hallucination spans usingdifferent prompting strategies, and the Fine-Tuning-Based Approach (FBA), which fine-tunes pre-trained Language Models (LMs) toextract hallucination spans in a supervised man-ner. Our experiments reveal that PBA, espe-cially when incorporating explicit references orexternal knowledge, outperforms FBA. How-ever, the effectiveness of PBA varies across lan-guages, likely due to differences in languagerepresentation within LLMs</abstract>
<identifier type="citekey">tufa-etal-2025-firc-nlp</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.273/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>2096</start>
<end>2102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FiRC-NLP at SemEval-2025 Task 3: Exploring Prompting Approaches for Detecting Hallucinations in LLMs
%A Tufa, Wondimagegnhue
%A Hassan, Fadi
%A Collell, Guillem
%A Tu, Dandan
%A Tu, Yi
%A Ni, Sang
%A Tan, Kuan Eeik
%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 tufa-etal-2025-firc-nlp
%X This paper presents a system description forthe SemEval Mu-SHROOM task, focusing ondetecting hallucination spans in the outputsof instruction-tuned Large Language Models(LLMs) across 14 languages. We comparetwo distinct approaches: Prompt-Based Ap-proach (PBA), which leverages the capabilityof LLMs to detect hallucination spans usingdifferent prompting strategies, and the Fine-Tuning-Based Approach (FBA), which fine-tunes pre-trained Language Models (LMs) toextract hallucination spans in a supervised man-ner. Our experiments reveal that PBA, espe-cially when incorporating explicit references orexternal knowledge, outperforms FBA. How-ever, the effectiveness of PBA varies across lan-guages, likely due to differences in languagerepresentation within LLMs
%U https://aclanthology.org/2025.semeval-1.273/
%P 2096-2102
Markdown (Informal)
[FiRC-NLP at SemEval-2025 Task 3: Exploring Prompting Approaches for Detecting Hallucinations in LLMs](https://aclanthology.org/2025.semeval-1.273/) (Tufa et al., SemEval 2025)
ACL