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.- Anthology ID:
- 2024.semeval-1.246
- Volume:
- Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1719–1726
- Language:
- URL:
- https://aclanthology.org/2024.semeval-1.246
- DOI:
- Cite (ACL):
- Monika Singh, Sujit Kumar, Tanveen ., and Sanasam Ranbir Singh. 2024. ClusterCore at SemEval-2024 Task 7: Few Shot Prompting With Large Language Models for Numeral-Aware Headline Generation. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1719–1726, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- ClusterCore at SemEval-2024 Task 7: Few Shot Prompting With Large Language Models for Numeral-Aware Headline Generation (Singh et al., SemEval 2024)
- PDF:
- https://preview.aclanthology.org/ingestion-checklist/2024.semeval-1.246.pdf