@inproceedings{saravanan-wilson-2024-ounlp,
title = "{OUNLP} at {S}em{E}val-2024 Task 9: Retrieval-Augmented Generation for Solving Brain Teasers with {LLM}s",
author = "Saravanan, Vineet and
Wilson, Steven",
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-1.32",
doi = "10.18653/v1/2024.semeval-1.32",
pages = "206--212",
abstract = "The advancement of natural language processing has given rise to a variety of large language models (LLMs) with capabilities extending into the realm of complex problem-solving, including brainteasers that challenge not only linguistic fluency but also logical reasoning. This paper documents our submission to the SemEval 2024 Brainteaser task, in which we investigate the performance of state-of-the-art LLMs, such as GPT-3.5, GPT-4, and the Gemini model, on a diverse set of brainteasers using prompt engineering as a tool to enhance the models{'} problem-solving abilities. We experimented with a series of structured prompts ranging from basic to those integrating task descriptions and explanations. Through a comparative analysis, we sought to determine which combinations of model and prompt yielded the highest accuracy in solving these puzzles. Our findings provide a snapshot of the current landscape of AI problem-solving and highlight the nuanced nature of LLM performance, influenced by both the complexity of the tasks and the sophistication of the prompts employed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saravanan-wilson-2024-ounlp">
<titleInfo>
<title>OUNLP at SemEval-2024 Task 9: Retrieval-Augmented Generation for Solving Brain Teasers with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vineet</namePart>
<namePart type="family">Saravanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Wilson</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>The advancement of natural language processing has given rise to a variety of large language models (LLMs) with capabilities extending into the realm of complex problem-solving, including brainteasers that challenge not only linguistic fluency but also logical reasoning. This paper documents our submission to the SemEval 2024 Brainteaser task, in which we investigate the performance of state-of-the-art LLMs, such as GPT-3.5, GPT-4, and the Gemini model, on a diverse set of brainteasers using prompt engineering as a tool to enhance the models’ problem-solving abilities. We experimented with a series of structured prompts ranging from basic to those integrating task descriptions and explanations. Through a comparative analysis, we sought to determine which combinations of model and prompt yielded the highest accuracy in solving these puzzles. Our findings provide a snapshot of the current landscape of AI problem-solving and highlight the nuanced nature of LLM performance, influenced by both the complexity of the tasks and the sophistication of the prompts employed.</abstract>
<identifier type="citekey">saravanan-wilson-2024-ounlp</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.32</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.32</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>206</start>
<end>212</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OUNLP at SemEval-2024 Task 9: Retrieval-Augmented Generation for Solving Brain Teasers with LLMs
%A Saravanan, Vineet
%A Wilson, Steven
%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 saravanan-wilson-2024-ounlp
%X The advancement of natural language processing has given rise to a variety of large language models (LLMs) with capabilities extending into the realm of complex problem-solving, including brainteasers that challenge not only linguistic fluency but also logical reasoning. This paper documents our submission to the SemEval 2024 Brainteaser task, in which we investigate the performance of state-of-the-art LLMs, such as GPT-3.5, GPT-4, and the Gemini model, on a diverse set of brainteasers using prompt engineering as a tool to enhance the models’ problem-solving abilities. We experimented with a series of structured prompts ranging from basic to those integrating task descriptions and explanations. Through a comparative analysis, we sought to determine which combinations of model and prompt yielded the highest accuracy in solving these puzzles. Our findings provide a snapshot of the current landscape of AI problem-solving and highlight the nuanced nature of LLM performance, influenced by both the complexity of the tasks and the sophistication of the prompts employed.
%R 10.18653/v1/2024.semeval-1.32
%U https://aclanthology.org/2024.semeval-1.32
%U https://doi.org/10.18653/v1/2024.semeval-1.32
%P 206-212
Markdown (Informal)
[OUNLP at SemEval-2024 Task 9: Retrieval-Augmented Generation for Solving Brain Teasers with LLMs](https://aclanthology.org/2024.semeval-1.32) (Saravanan & Wilson, SemEval 2024)
ACL