@inproceedings{pukemo-etal-2025-iai,
title = "iai{\_}{MSU} at {S}em{E}val-2025 Task-3: Mu-{SHROOM}, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes in {E}nglish",
author = "Pukemo, Mikhail and
Levykin, Aleksandr and
Melikhov, Dmitrii and
Skiba, Gleb and
Ischenko, Roman and
Vorontsov, Konstantin",
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-1.28/",
pages = "193--197",
ISBN = "979-8-89176-273-2",
abstract = "This paper presents the submissions of the iai{\_}MSU team for SemEval-2025 Task 3 {--} Mu-SHROOM, where we achieved first place in the English language. The task involves detecting hallucinations in model-generated text, which requires systems to verify claims against reliable sources.In this paper, we present our approach to hallucination detection, which employs a three-stage system. The first stage uses a retrieval-based (Lewis et al., 2021) to verify claims against external knowledge sources. The second stage applies the Self-Refine Prompting (Madaan et al., 2023) to improve detection accuracy by analyzing potential errors of the first stage. The third stage combines predictions from the first and second stages into an ensemble.Our system achieves state-of-the-art performance on the competition dataset, demonstrating the effectiveness of combining retrieval-augmented verification with Self-Refine Prompting. The code for the solutions is available on https://github.com/pansershrek/IAI{\_}MSU."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pukemo-etal-2025-iai">
<titleInfo>
<title>iai_MSU at SemEval-2025 Task-3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes in English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Pukemo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandr</namePart>
<namePart type="family">Levykin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrii</namePart>
<namePart type="family">Melikhov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gleb</namePart>
<namePart type="family">Skiba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Ischenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Vorontsov</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 the submissions of the iai_MSU team for SemEval-2025 Task 3 – Mu-SHROOM, where we achieved first place in the English language. The task involves detecting hallucinations in model-generated text, which requires systems to verify claims against reliable sources.In this paper, we present our approach to hallucination detection, which employs a three-stage system. The first stage uses a retrieval-based (Lewis et al., 2021) to verify claims against external knowledge sources. The second stage applies the Self-Refine Prompting (Madaan et al., 2023) to improve detection accuracy by analyzing potential errors of the first stage. The third stage combines predictions from the first and second stages into an ensemble.Our system achieves state-of-the-art performance on the competition dataset, demonstrating the effectiveness of combining retrieval-augmented verification with Self-Refine Prompting. The code for the solutions is available on https://github.com/pansershrek/IAI_MSU.</abstract>
<identifier type="citekey">pukemo-etal-2025-iai</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.28/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>193</start>
<end>197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T iai_MSU at SemEval-2025 Task-3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes in English
%A Pukemo, Mikhail
%A Levykin, Aleksandr
%A Melikhov, Dmitrii
%A Skiba, Gleb
%A Ischenko, Roman
%A Vorontsov, Konstantin
%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 pukemo-etal-2025-iai
%X This paper presents the submissions of the iai_MSU team for SemEval-2025 Task 3 – Mu-SHROOM, where we achieved first place in the English language. The task involves detecting hallucinations in model-generated text, which requires systems to verify claims against reliable sources.In this paper, we present our approach to hallucination detection, which employs a three-stage system. The first stage uses a retrieval-based (Lewis et al., 2021) to verify claims against external knowledge sources. The second stage applies the Self-Refine Prompting (Madaan et al., 2023) to improve detection accuracy by analyzing potential errors of the first stage. The third stage combines predictions from the first and second stages into an ensemble.Our system achieves state-of-the-art performance on the competition dataset, demonstrating the effectiveness of combining retrieval-augmented verification with Self-Refine Prompting. The code for the solutions is available on https://github.com/pansershrek/IAI_MSU.
%U https://aclanthology.org/2025.semeval-1.28/
%P 193-197
Markdown (Informal)
[iai_MSU at SemEval-2025 Task-3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes in English](https://aclanthology.org/2025.semeval-1.28/) (Pukemo et al., SemEval 2025)
ACL