@inproceedings{alberts-etal-2025-fenji,
title = "{FENJI} at {S}em{E}val-2025 Task 3: Retrieval-Augmented Generation and Hallucination Span Detection",
author = "Alberts, Flor and
Bruinier, Ivo and
Palm, Nathalie and
Paetzelt, Justin and
Varecha, Erik",
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-1.151/",
pages = "1143--1151",
ISBN = "979-8-89176-273-2",
abstract = "Large Language Models (LLMs) have significantly advanced Natural Language Processing, however, ensuring the factual reliability of these models remains a challenge, as they are prone to hallucination - generating text that appears coherent but contains innacurate or unsupported information. SemEval-2025 Mu-SHROOM focused on character-level hallucination detection in 14 languages. In this task, participants were required to pinpoint hallucinated spans in text generated by multiple instruction-tuned LLMs. Our team created a system that leveraged a Retrieval-Augmented Generation (RAG) approach and prompting a FLAN-T5 model to identify hallucination spans. Despite contradicting prior literature, our approach yielded disappointing results, underperforming all the ``mark-all'' baselines and failing to achieve competitive scores. Notably, removing RAG improved performance. The findings highlight that while RAG holds potential for hallucination detection, its effectiveness is heavily influenced by the retrieval component{'}s context-awareness. Enhancing the RAG{'}s ability to capture more comprehensive contextual information could improve performance across languages, making it a more reliable tool for identifying hallucination spans."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alberts-etal-2025-fenji">
<titleInfo>
<title>FENJI at SemEval-2025 Task 3: Retrieval-Augmented Generation and Hallucination Span Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="family">Alberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivo</namePart>
<namePart type="family">Bruinier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathalie</namePart>
<namePart type="family">Palm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Paetzelt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Varecha</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>Large Language Models (LLMs) have significantly advanced Natural Language Processing, however, ensuring the factual reliability of these models remains a challenge, as they are prone to hallucination - generating text that appears coherent but contains innacurate or unsupported information. SemEval-2025 Mu-SHROOM focused on character-level hallucination detection in 14 languages. In this task, participants were required to pinpoint hallucinated spans in text generated by multiple instruction-tuned LLMs. Our team created a system that leveraged a Retrieval-Augmented Generation (RAG) approach and prompting a FLAN-T5 model to identify hallucination spans. Despite contradicting prior literature, our approach yielded disappointing results, underperforming all the “mark-all” baselines and failing to achieve competitive scores. Notably, removing RAG improved performance. The findings highlight that while RAG holds potential for hallucination detection, its effectiveness is heavily influenced by the retrieval component’s context-awareness. Enhancing the RAG’s ability to capture more comprehensive contextual information could improve performance across languages, making it a more reliable tool for identifying hallucination spans.</abstract>
<identifier type="citekey">alberts-etal-2025-fenji</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.151/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1143</start>
<end>1151</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FENJI at SemEval-2025 Task 3: Retrieval-Augmented Generation and Hallucination Span Detection
%A Alberts, Flor
%A Bruinier, Ivo
%A Palm, Nathalie
%A Paetzelt, Justin
%A Varecha, Erik
%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 alberts-etal-2025-fenji
%X Large Language Models (LLMs) have significantly advanced Natural Language Processing, however, ensuring the factual reliability of these models remains a challenge, as they are prone to hallucination - generating text that appears coherent but contains innacurate or unsupported information. SemEval-2025 Mu-SHROOM focused on character-level hallucination detection in 14 languages. In this task, participants were required to pinpoint hallucinated spans in text generated by multiple instruction-tuned LLMs. Our team created a system that leveraged a Retrieval-Augmented Generation (RAG) approach and prompting a FLAN-T5 model to identify hallucination spans. Despite contradicting prior literature, our approach yielded disappointing results, underperforming all the “mark-all” baselines and failing to achieve competitive scores. Notably, removing RAG improved performance. The findings highlight that while RAG holds potential for hallucination detection, its effectiveness is heavily influenced by the retrieval component’s context-awareness. Enhancing the RAG’s ability to capture more comprehensive contextual information could improve performance across languages, making it a more reliable tool for identifying hallucination spans.
%U https://aclanthology.org/2025.semeval-1.151/
%P 1143-1151
Markdown (Informal)
[FENJI at SemEval-2025 Task 3: Retrieval-Augmented Generation and Hallucination Span Detection](https://aclanthology.org/2025.semeval-1.151/) (Alberts et al., SemEval 2025)
ACL