@inproceedings{chakraborty-etal-2024-deja,
title = "Deja Vu at {S}em{E}val 2024 Task 9: A Comparative Study of Advanced Language Models for Commonsense Reasoning",
author = "Chakraborty, Trina and
Rahman, Marufur and
Riyad, Omar",
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-1.180",
doi = "10.18653/v1/2024.semeval-1.180",
pages = "1239--1244",
abstract = "This research systematically forms an impression of the capabilities of advanced language models in addressing the BRAINTEASER task introduced at SemEval 2024, which is specifically designed to explore the models{'} proficiency in lateral commonsense reasoning. The task sets forth an array of Sentence and Word Puzzles, carefully crafted to challenge the models with scenarios requiring unconventional thought processes. Our methodology encompasses a holistic approach, incorporating pre-processing of data, fine-tuning of transformer-based language models, and strategic data augmentation to explore the depth and flexibility of each model{'}s understanding. The preliminary results of our analysis are encouraging, highlighting significant potential for advancements in the models{'} ability to engage in lateral reasoning. Further insights gained from post-competition evaluations suggest scopes for notable enhancements in model performance, emphasizing the continuous evolution of the models in mastering complex reasoning tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chakraborty-etal-2024-deja">
<titleInfo>
<title>Deja Vu at SemEval 2024 Task 9: A Comparative Study of Advanced Language Models for Commonsense Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trina</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marufur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Riyad</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 research systematically forms an impression of the capabilities of advanced language models in addressing the BRAINTEASER task introduced at SemEval 2024, which is specifically designed to explore the models’ proficiency in lateral commonsense reasoning. The task sets forth an array of Sentence and Word Puzzles, carefully crafted to challenge the models with scenarios requiring unconventional thought processes. Our methodology encompasses a holistic approach, incorporating pre-processing of data, fine-tuning of transformer-based language models, and strategic data augmentation to explore the depth and flexibility of each model’s understanding. The preliminary results of our analysis are encouraging, highlighting significant potential for advancements in the models’ ability to engage in lateral reasoning. Further insights gained from post-competition evaluations suggest scopes for notable enhancements in model performance, emphasizing the continuous evolution of the models in mastering complex reasoning tasks.</abstract>
<identifier type="citekey">chakraborty-etal-2024-deja</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.180</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.180</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1239</start>
<end>1244</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Deja Vu at SemEval 2024 Task 9: A Comparative Study of Advanced Language Models for Commonsense Reasoning
%A Chakraborty, Trina
%A Rahman, Marufur
%A Riyad, Omar
%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 chakraborty-etal-2024-deja
%X This research systematically forms an impression of the capabilities of advanced language models in addressing the BRAINTEASER task introduced at SemEval 2024, which is specifically designed to explore the models’ proficiency in lateral commonsense reasoning. The task sets forth an array of Sentence and Word Puzzles, carefully crafted to challenge the models with scenarios requiring unconventional thought processes. Our methodology encompasses a holistic approach, incorporating pre-processing of data, fine-tuning of transformer-based language models, and strategic data augmentation to explore the depth and flexibility of each model’s understanding. The preliminary results of our analysis are encouraging, highlighting significant potential for advancements in the models’ ability to engage in lateral reasoning. Further insights gained from post-competition evaluations suggest scopes for notable enhancements in model performance, emphasizing the continuous evolution of the models in mastering complex reasoning tasks.
%R 10.18653/v1/2024.semeval-1.180
%U https://aclanthology.org/2024.semeval-1.180
%U https://doi.org/10.18653/v1/2024.semeval-1.180
%P 1239-1244
Markdown (Informal)
[Deja Vu at SemEval 2024 Task 9: A Comparative Study of Advanced Language Models for Commonsense Reasoning](https://aclanthology.org/2024.semeval-1.180) (Chakraborty et al., SemEval 2024)
ACL