SubmissionNumber#=%=#108
FinalPaperTitle#=%=#Team NP_PROBLEM at SemEval-2024 Task 7: Numerical Reasoning in Headline Generation with Preference Optimization
ShortPaperTitle#=%=#
NumberOfPages#=%=#5
CopyrightSigned#=%=#Nut Chukamphaeng
JobTitle#==#
Organization#==#
Abstract#==#While large language models (LLMs) exhibit impressive linguistic abilities, their numerical reasoning skills within real-world contexts re- main under-explored. This paper describes our participation in a headline-generation challenge by Numeval at Semeval 2024, which focused on numerical reasoning. Our system achieved an overall top numerical accuracy of 73.49% on the task. We explore the system's design choices contributing to this result and analyze common error patterns. Our findings highlight the potential and ongoing challenges of integrat- ing numerical reasoning within large language model-based headline generation.
Author{1}{Firstname}#=%=#Pawan Kumar
Author{1}{Lastname}#=%=#Rajpoot
Author{1}{Username}#=%=#pawan2411
Author{1}{Email}#=%=#pawan.rajpoot2411@gmail.com
Author{1}{Affiliation}#=%=#Self
Author{2}{Firstname}#=%=#Nut
Author{2}{Lastname}#=%=#Chukamphaeng
Author{2}{Username}#=%=#nutorbit
Author{2}{Email}#=%=#nutorbitx@gmail.com
Author{2}{Affiliation}#=%=#SCB DataX

==========
èéáğö