Biomedical summarization requires large datasets to train for text generation. We show that while transfer learning offers a viable option for addressing this challenge, an in-domain pre-training does not always offer advantages in a BioASQ summarization task. We identify a suitable model architecture and use it to show a benefit of a general-domain pre-training followed by a task-specific fine-tuning in the context of a BioASQ summarization task, leading to a novel three-step fine-tuning approach that works with only a thousand in-domain examples. Our results indicate that a Large Language Model without domain-specific pre-training can have a significant edge in some domain-specific biomedical text generation tasks.
@article{arxiv.2307.04412,
title = {Enhancing Biomedical Text Summarization and Question-Answering: On the Utility of Domain-Specific Pre-Training},
author = {Dima Galat and Marian-Andrei Rizoiu},
journal= {arXiv preprint arXiv:2307.04412},
year = {2023}
}