@inproceedings{take-tran-2024-riddlemasters,
title = "{R}iddle{M}asters at {S}em{E}val-2024 Task 9: Comparing Instruction Fine-tuning with Zero-Shot Approaches",
author = "Take, Kejsi and
Tran, Chau",
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-1.200",
pages = "1391--1396",
abstract = "This paper describes our contribution to SemEval 2023 Task 8: Brainteaser. We compared multiple zero-shot approaches using GPT-4, the state of the art model with Mistral-7B, a much smaller open-source LLM. While GPT-4 remains a clear winner in all the zero-shot approaches, we show that finetuning Mistral-7B can achieve comparable, even though marginally lower results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="take-tran-2024-riddlemasters">
<titleInfo>
<title>RiddleMasters at SemEval-2024 Task 9: Comparing Instruction Fine-tuning with Zero-Shot Approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kejsi</namePart>
<namePart type="family">Take</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chau</namePart>
<namePart type="family">Tran</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 paper describes our contribution to SemEval 2023 Task 8: Brainteaser. We compared multiple zero-shot approaches using GPT-4, the state of the art model with Mistral-7B, a much smaller open-source LLM. While GPT-4 remains a clear winner in all the zero-shot approaches, we show that finetuning Mistral-7B can achieve comparable, even though marginally lower results.</abstract>
<identifier type="citekey">take-tran-2024-riddlemasters</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.200</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1391</start>
<end>1396</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RiddleMasters at SemEval-2024 Task 9: Comparing Instruction Fine-tuning with Zero-Shot Approaches
%A Take, Kejsi
%A Tran, Chau
%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 take-tran-2024-riddlemasters
%X This paper describes our contribution to SemEval 2023 Task 8: Brainteaser. We compared multiple zero-shot approaches using GPT-4, the state of the art model with Mistral-7B, a much smaller open-source LLM. While GPT-4 remains a clear winner in all the zero-shot approaches, we show that finetuning Mistral-7B can achieve comparable, even though marginally lower results.
%U https://aclanthology.org/2024.semeval-1.200
%P 1391-1396
Markdown (Informal)
[RiddleMasters at SemEval-2024 Task 9: Comparing Instruction Fine-tuning with Zero-Shot Approaches](https://aclanthology.org/2024.semeval-1.200) (Take & Tran, SemEval 2024)
ACL