SubmissionNumber#=%=#35
FinalPaperTitle#=%=#ZXQ at SemEval-2024 Task 7 Fine-tuning GPT-3.5-Turbo for Numerical Reasoning
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Zhen Qian
JobTitle#==#
Organization#==#
Abstract#==#In this paper, we present our system for the NumEval@SemEval-2024 Task 3: Numerical Reasoning. Given a news article and its headline, the numerical reasoning task involves creating a system to compute the intentionally excluded number within the news headline. We propose a fine-tuned GPT-3.5-turbo model, specifically engineered to deduce missing numerals directly from the content of news articles. The model is trained with a human-engineered prompt that integrates the news content and the masked headline, tailoring its accuracy for the designated task. It achieves an accuracy of 0.94 on the test data and secures the second position in the official leaderboard. An examination on the system's inference results reveals its commendable accuracy in identifying correct numerals when they can be directly "copied" from the articles. However, the error rates increase when it comes to some ambiguous operations such as rounding.
Author{1}{Firstname}#=%=#Zhen
Author{1}{Lastname}#=%=#Qian
Author{1}{Username}#=%=#zhen.qian1992
Author{1}{Email}#=%=#s3888611@student.rmit.edu.au
Author{1}{Affiliation}#=%=#Royal Melbourne Institute of Technology
Author{2}{Firstname}#=%=#Xiaofei
Author{2}{Lastname}#=%=#Xu
Author{2}{Email}#=%=#S3833028@student.rmit.edu.au
Author{2}{Affiliation}#=%=#Royal Melbourne Institute of Technology
Author{3}{Firstname}#=%=#Xiuzhen
Author{3}{Lastname}#=%=#Zhang
Author{3}{Username}#=%=#xiuzhen.zhang
Author{3}{Email}#=%=#xiuzhen.zhang@rmit.edu.au
Author{3}{Affiliation}#=%=#RMIT University

==========
èéáğö