@inproceedings{singh-etal-2024-clustercore,
    title = "{C}luster{C}ore at {S}em{E}val-2024 Task 7: Few Shot Prompting With Large Language Models for Numeral-Aware Headline Generation",
    author = "Singh, Monika  and
      Kumar, Sujit  and
      ., Tanveen  and
      Ranbir Singh, Sanasam",
    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://preview.aclanthology.org/jlcl-multiple-ingestion/2024.semeval-1.246/",
    doi = "10.18653/v1/2024.semeval-1.246",
    pages = "1719--1726",
    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."
}