Investigating Large Language Models and Control Mechanisms to Improve Text Readability of Biomedical Abstracts

arXiv:2309.13202v2 Announce Type: replace
Abstract: Biomedical literature often uses complex language and inaccessible professional terminologies. That is why simplification plays an important role in improving public health literacy. Applying Natural Language Processing (NLP) models to automate such tasks allows for quick and direct accessibility for lay readers. In this work, we investigate the ability of state-of-the-art large language models (LLMs) on the task of biomedical abstract simplification, using the publicly available dataset for plain language adaptation of biomedical abstracts (\textbf{PLABA}). …

arxiv biomedical control cs.ai cs.cl language language models large language large language models readability text type