@inproceedings{mehta-etal-2024-halu,
title = "Halu-{NLP} at {S}em{E}val-2024 Task 6: {M}eta{C}heck{GPT} - A Multi-task Hallucination Detection using {LLM} uncertainty and meta-models",
author = "Mehta, Rahul and
Hoblitzell, Andrew and
O{'}keefe, Jack and
Jang, Hyeju and
Varma, Vasudeva",
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-1.52/",
doi = "10.18653/v1/2024.semeval-1.52",
pages = "342--348",
abstract = "Hallucinations in large language models(LLMs) have recently become a significantproblem. A recent effort in this directionis a shared task at Semeval 2024 Task 6,SHROOM, a Shared-task on Hallucinationsand Related Observable Overgeneration Mis-takes. This paper describes our winning so-lution ranked 1st and 2nd in the 2 sub-tasksof model agnostic and model aware tracks re-spectively. We propose a meta-regressor basedensemble of LLMs based on a random forestalgorithm that achieves the highest scores onthe leader board. We also experiment with var-ious transformer based models and black boxmethods like ChatGPT, Vectara, and others. Inaddition, we perform an error analysis com-paring ChatGPT against our best model whichshows the limitations of the former"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehta-etal-2024-halu">
<titleInfo>
<title>Halu-NLP at SemEval-2024 Task 6: MetaCheckGPT - A Multi-task Hallucination Detection using LLM uncertainty and meta-models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Mehta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Hoblitzell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">O’keefe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeju</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasudeva</namePart>
<namePart type="family">Varma</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>Hallucinations in large language models(LLMs) have recently become a significantproblem. A recent effort in this directionis a shared task at Semeval 2024 Task 6,SHROOM, a Shared-task on Hallucinationsand Related Observable Overgeneration Mis-takes. This paper describes our winning so-lution ranked 1st and 2nd in the 2 sub-tasksof model agnostic and model aware tracks re-spectively. We propose a meta-regressor basedensemble of LLMs based on a random forestalgorithm that achieves the highest scores onthe leader board. We also experiment with var-ious transformer based models and black boxmethods like ChatGPT, Vectara, and others. Inaddition, we perform an error analysis com-paring ChatGPT against our best model whichshows the limitations of the former</abstract>
<identifier type="citekey">mehta-etal-2024-halu</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.52</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.52/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>342</start>
<end>348</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Halu-NLP at SemEval-2024 Task 6: MetaCheckGPT - A Multi-task Hallucination Detection using LLM uncertainty and meta-models
%A Mehta, Rahul
%A Hoblitzell, Andrew
%A O’keefe, Jack
%A Jang, Hyeju
%A Varma, Vasudeva
%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 mehta-etal-2024-halu
%X Hallucinations in large language models(LLMs) have recently become a significantproblem. A recent effort in this directionis a shared task at Semeval 2024 Task 6,SHROOM, a Shared-task on Hallucinationsand Related Observable Overgeneration Mis-takes. This paper describes our winning so-lution ranked 1st and 2nd in the 2 sub-tasksof model agnostic and model aware tracks re-spectively. We propose a meta-regressor basedensemble of LLMs based on a random forestalgorithm that achieves the highest scores onthe leader board. We also experiment with var-ious transformer based models and black boxmethods like ChatGPT, Vectara, and others. Inaddition, we perform an error analysis com-paring ChatGPT against our best model whichshows the limitations of the former
%R 10.18653/v1/2024.semeval-1.52
%U https://aclanthology.org/2024.semeval-1.52/
%U https://doi.org/10.18653/v1/2024.semeval-1.52
%P 342-348
Markdown (Informal)
[Halu-NLP at SemEval-2024 Task 6: MetaCheckGPT - A Multi-task Hallucination Detection using LLM uncertainty and meta-models](https://aclanthology.org/2024.semeval-1.52/) (Mehta et al., SemEval 2024)
ACL