@inproceedings{kelious-okirim-2024-abdelhak,
title = "Abdelhak at {S}em{E}val-2024 Task 9: Decoding Brainteasers, The Efficacy of Dedicated Models Versus {C}hat{GPT}",
author = "Kelious, Abdelhak and
Okirim, Mounir",
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-1.31",
doi = "10.18653/v1/2024.semeval-1.31",
pages = "200--205",
abstract = "This study introduces a dedicated model aimed at solving the BRAINTEASER task 9 , a novel challenge designed to assess models{'} lateral thinking capabilities through sentence and word puzzles. Our model demonstrates remarkable efficacy, securing Rank 1 in sentence puzzle solving during the test phase with an overall score of 0.98. Additionally, we explore the comparative performance of ChatGPT, specifically analyzing how variations in temperature settings affect its ability to engage in lateral thinking and problem-solving. Our findings indicate a notable performance disparity between the dedicated model and ChatGPT, underscoring the potential of specialized approaches in enhancing creative reasoning in AI.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kelious-okirim-2024-abdelhak">
<titleInfo>
<title>Abdelhak at SemEval-2024 Task 9: Decoding Brainteasers, The Efficacy of Dedicated Models Versus ChatGPT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdelhak</namePart>
<namePart type="family">Kelious</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mounir</namePart>
<namePart type="family">Okirim</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>This study introduces a dedicated model aimed at solving the BRAINTEASER task 9 , a novel challenge designed to assess models’ lateral thinking capabilities through sentence and word puzzles. Our model demonstrates remarkable efficacy, securing Rank 1 in sentence puzzle solving during the test phase with an overall score of 0.98. Additionally, we explore the comparative performance of ChatGPT, specifically analyzing how variations in temperature settings affect its ability to engage in lateral thinking and problem-solving. Our findings indicate a notable performance disparity between the dedicated model and ChatGPT, underscoring the potential of specialized approaches in enhancing creative reasoning in AI.</abstract>
<identifier type="citekey">kelious-okirim-2024-abdelhak</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.31</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.31</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>200</start>
<end>205</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Abdelhak at SemEval-2024 Task 9: Decoding Brainteasers, The Efficacy of Dedicated Models Versus ChatGPT
%A Kelious, Abdelhak
%A Okirim, Mounir
%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 kelious-okirim-2024-abdelhak
%X This study introduces a dedicated model aimed at solving the BRAINTEASER task 9 , a novel challenge designed to assess models’ lateral thinking capabilities through sentence and word puzzles. Our model demonstrates remarkable efficacy, securing Rank 1 in sentence puzzle solving during the test phase with an overall score of 0.98. Additionally, we explore the comparative performance of ChatGPT, specifically analyzing how variations in temperature settings affect its ability to engage in lateral thinking and problem-solving. Our findings indicate a notable performance disparity between the dedicated model and ChatGPT, underscoring the potential of specialized approaches in enhancing creative reasoning in AI.
%R 10.18653/v1/2024.semeval-1.31
%U https://aclanthology.org/2024.semeval-1.31
%U https://doi.org/10.18653/v1/2024.semeval-1.31
%P 200-205
Markdown (Informal)
[Abdelhak at SemEval-2024 Task 9: Decoding Brainteasers, The Efficacy of Dedicated Models Versus ChatGPT](https://aclanthology.org/2024.semeval-1.31) (Kelious & Okirim, SemEval 2024)
ACL