DeakinNLP at BioLaySumm: Evaluating Fine-tuning Longformer and GPT-4 Prompting for Biomedical Lay Summarization

Huy Quoc To, Ming Liu, Guangyan Huang


Abstract
This paper presents our approaches for the BioLaySumm 2024 Shared Task. We evaluate two methods for generating lay summaries based on biomedical articles: (1) fine-tuning the Longformer-Encoder-Decoder (LED) model, and (2) zero-shot and few-shot prompting on GPT-4. In the fine-tuning approach, we individually fine-tune the LED model using two datasets: PLOS and eLife. This process is conducted under two different settings: one utilizing 50% of the training dataset, and the other utilizing the entire 100% of the training dataset. We compare the results of both methods with GPT-4 in zero-shot and few-shot prompting. The experiment results demonstrate that fine-tuning with 100% of the training data achieves better performance than prompting with GPT-4. However, under data scarcity circumstances, prompting GPT-4 seems to be a better solution.
Anthology ID:
2024.bionlp-1.67
Volume:
Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Dina Demner-Fushman, Sophia Ananiadou, Makoto Miwa, Kirk Roberts, Junichi Tsujii
Venues:
BioNLP | WS
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
748–754
Language:
URL:
https://aclanthology.org/2024.bionlp-1.67
DOI:
10.18653/v1/2024.bionlp-1.67
Bibkey:
Cite (ACL):
Huy Quoc To, Ming Liu, and Guangyan Huang. 2024. DeakinNLP at BioLaySumm: Evaluating Fine-tuning Longformer and GPT-4 Prompting for Biomedical Lay Summarization. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 748–754, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
DeakinNLP at BioLaySumm: Evaluating Fine-tuning Longformer and GPT-4 Prompting for Biomedical Lay Summarization (To et al., BioNLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.bionlp-1.67.pdf