@inproceedings{abdallah-el-beltagy-2025-hallusearch,
title = "{H}allu{S}earch at {S}em{E}val-2025 Task 3: A Search-Enhanced {RAG} Pipeline for Hallucination Detection",
author = "Abdallah, Mohamed and
El - Beltagy, Samhaa",
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-1.189/",
pages = "1436--1441",
ISBN = "979-8-89176-273-2",
abstract = "We present HalluSearch, a multilingual pipeline designed to detect fabricated text spans in Large Language Model (LLM) outputs as part of Mu-SHROOM. HalluSearch couples retrieval-augmented verification with fine-grained factual splitting to identify and localize hallucinations in 14 different languages. Empirical evaluations show that HalluSearch performs competitively, placing fourth in both English (within the top 10{\%}) and Czech. While the system{'}s retrieval-based strategy generally proves robust, it faces challenges in languages with limited online coverage, underscoring the need for further research to ensure consistent hallucination detection across diverse linguistic contexts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdallah-el-beltagy-2025-hallusearch">
<titleInfo>
<title>HalluSearch at SemEval-2025 Task 3: A Search-Enhanced RAG Pipeline for Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Abdallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El - Beltagy</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>We present HalluSearch, a multilingual pipeline designed to detect fabricated text spans in Large Language Model (LLM) outputs as part of Mu-SHROOM. HalluSearch couples retrieval-augmented verification with fine-grained factual splitting to identify and localize hallucinations in 14 different languages. Empirical evaluations show that HalluSearch performs competitively, placing fourth in both English (within the top 10%) and Czech. While the system’s retrieval-based strategy generally proves robust, it faces challenges in languages with limited online coverage, underscoring the need for further research to ensure consistent hallucination detection across diverse linguistic contexts.</abstract>
<identifier type="citekey">abdallah-el-beltagy-2025-hallusearch</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.189/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1436</start>
<end>1441</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HalluSearch at SemEval-2025 Task 3: A Search-Enhanced RAG Pipeline for Hallucination Detection
%A Abdallah, Mohamed
%A El - Beltagy, Samhaa
%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 abdallah-el-beltagy-2025-hallusearch
%X We present HalluSearch, a multilingual pipeline designed to detect fabricated text spans in Large Language Model (LLM) outputs as part of Mu-SHROOM. HalluSearch couples retrieval-augmented verification with fine-grained factual splitting to identify and localize hallucinations in 14 different languages. Empirical evaluations show that HalluSearch performs competitively, placing fourth in both English (within the top 10%) and Czech. While the system’s retrieval-based strategy generally proves robust, it faces challenges in languages with limited online coverage, underscoring the need for further research to ensure consistent hallucination detection across diverse linguistic contexts.
%U https://aclanthology.org/2025.semeval-1.189/
%P 1436-1441
Markdown (Informal)
[HalluSearch at SemEval-2025 Task 3: A Search-Enhanced RAG Pipeline for Hallucination Detection](https://aclanthology.org/2025.semeval-1.189/) (Abdallah & El - Beltagy, SemEval 2025)
ACL