SubmissionNumber#=%=#262
FinalPaperTitle#=%=#ClusterCore at SemEval-2024 Task 7: Few Shot Prompting With Large Language Models for Numeral-Aware Headline Generation
ShortPaperTitle#=%=#
NumberOfPages#=%=#8
CopyrightSigned#=%=#sujit kumar
JobTitle#==#
Organization#==#
Abstract#==#The generation of headlines, a crucial aspect of abstractive summarization, aims to compress an entire article into a concise, single line of text despite the effectiveness of modern encoder-decoder models for text generation and summarization tasks. The encoder-decoder model commonly faces challenges in accurately generating numerical content within headlines. This study empirically explored LLMs for numeral-aware headline generation and proposed few-shot prompting with LLMs for numeral-aware headline generations. Experiments conducted on the NumHG dataset and NumEval-2024 test set suggest that fine-tuning LLMs on NumHG dataset enhances the performance of LLMs for numeral aware headline generation. Furthermore, few-shot prompting with LLMs surpassed the performance of fine-tuned LLMs for numeral-aware headline generation.
Author{1}{Firstname}#=%=#Monika
Author{1}{Lastname}#=%=#Singh
Author{1}{Email}#=%=#s.monika@iitg.ac.in
Author{1}{Affiliation}#=%=#Indian Institute of Technology Guwahati
Author{2}{Firstname}#=%=#Sujit
Author{2}{Lastname}#=%=#Kumar
Author{2}{Username}#=%=#sujitkumar
Author{2}{Email}#=%=#sujitkumar@iitg.ac.in
Author{2}{Affiliation}#=%=#Research Scholar, Indian Institute of Technology Guwahati
Author{3}{Lastname}#=%=#Tanveen
Author{3}{Email}#=%=#t.tanveen@iitg.ac.in
Author{3}{Affiliation}#=%=#Indian Institute of Technology Guwahati
Author{4}{Firstname}#=%=#Sanasam
Author{4}{Lastname}#=%=#Ranbir Singh
Author{4}{Username}#=%=#ranbir
Author{4}{Email}#=%=#ranbir@iitg.ernet.in
Author{4}{Affiliation}#=%=#Indian Institute of Technology Guwahati

==========
èéáğö