SubmissionNumber#=%=#209
FinalPaperTitle#=%=#RiddleMasters at SemEval-2024 Task 9: Comparing Instruction Fine-tuning with Zero-Shot Approaches
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Kejsi Take
JobTitle#==#
Organization#==#
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.
Author{1}{Firstname}#=%=#Kejsi
Author{1}{Lastname}#=%=#Take
Author{1}{Username}#=%=#kejsit
Author{1}{Email}#=%=#kejsitake@nyu.edu
Author{1}{Affiliation}#=%=#New York University
Author{2}{Firstname}#=%=#Chau
Author{2}{Lastname}#=%=#Tran
Author{2}{Email}#=%=#cpt289@nyu.edu
Author{2}{Affiliation}#=%=#New York University

==========
èéáğö