@inproceedings{rykov-etal-2024-smurfcat,
title = "{S}murf{C}at at {S}em{E}val-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection",
author = "Rykov, Elisei and
Shishkina, Yana and
Petrushina, Ksenia and
Titova, Ksenia and
Petrakov, Sergey and
Panchenko, Alexander",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.125",
doi = "10.18653/v1/2024.semeval-1.125",
pages = "869--880",
abstract = "In this paper, we present our novel systems developed for the SemEval-2024 hallucination detection task. Our investigation spans a range of strategies to compare model predictions with reference standards, encompassing diverse baselines, the refinement of pre-trained encoders through supervised learning, and an ensemble approaches utilizing several high-performing models. Through these explorations, we introduce three distinct methods that exhibit strong performance metrics. To amplify our training data, we generate additional training samples from unlabelled training subset. Furthermore, we provide a detailed comparative analysis of our approaches. Notably, our premier method achieved a commendable 9th place in the competition{'}s model-agnostic track and 20th place in model-aware track, highlighting its effectiveness and potential.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rykov-etal-2024-smurfcat">
<titleInfo>
<title>SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elisei</namePart>
<namePart type="family">Rykov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yana</namePart>
<namePart type="family">Shishkina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ksenia</namePart>
<namePart type="family">Petrushina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ksenia</namePart>
<namePart type="family">Titova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergey</namePart>
<namePart type="family">Petrakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present our novel systems developed for the SemEval-2024 hallucination detection task. Our investigation spans a range of strategies to compare model predictions with reference standards, encompassing diverse baselines, the refinement of pre-trained encoders through supervised learning, and an ensemble approaches utilizing several high-performing models. Through these explorations, we introduce three distinct methods that exhibit strong performance metrics. To amplify our training data, we generate additional training samples from unlabelled training subset. Furthermore, we provide a detailed comparative analysis of our approaches. Notably, our premier method achieved a commendable 9th place in the competition’s model-agnostic track and 20th place in model-aware track, highlighting its effectiveness and potential.</abstract>
<identifier type="citekey">rykov-etal-2024-smurfcat</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.125</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.125</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>869</start>
<end>880</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection
%A Rykov, Elisei
%A Shishkina, Yana
%A Petrushina, Ksenia
%A Titova, Ksenia
%A Petrakov, Sergey
%A Panchenko, Alexander
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F rykov-etal-2024-smurfcat
%X In this paper, we present our novel systems developed for the SemEval-2024 hallucination detection task. Our investigation spans a range of strategies to compare model predictions with reference standards, encompassing diverse baselines, the refinement of pre-trained encoders through supervised learning, and an ensemble approaches utilizing several high-performing models. Through these explorations, we introduce three distinct methods that exhibit strong performance metrics. To amplify our training data, we generate additional training samples from unlabelled training subset. Furthermore, we provide a detailed comparative analysis of our approaches. Notably, our premier method achieved a commendable 9th place in the competition’s model-agnostic track and 20th place in model-aware track, highlighting its effectiveness and potential.
%R 10.18653/v1/2024.semeval-1.125
%U https://aclanthology.org/2024.semeval-1.125
%U https://doi.org/10.18653/v1/2024.semeval-1.125
%P 869-880
Markdown (Informal)
[SmurfCat at SemEval-2024 Task 6: Leveraging Synthetic Data for Hallucination Detection](https://aclanthology.org/2024.semeval-1.125) (Rykov et al., SemEval 2024)
ACL