Adapting Biomedical Abstracts into Plain language using Large Language Models

TL;DR

This paper presents a system that uses fine-tuned large language models, including GPT-4, to convert biomedical abstracts into plain language suitable for the general public, improving health literacy and accessibility.

Contribution

It introduces a novel approach leveraging open-source large language models for biomedical abstract simplification, with a focus on dialog-based adaptation and evaluation.

Findings

GPT-4 based model ranked first in simplicity

Achieved third place in accuracy among participants

Demonstrated effective adaptation of biomedical abstracts into plain language

Abstract

A vast amount of medical knowledge is available for public use through online health forums, and question-answering platforms on social media. The majority of the population in the United States doesn't have the right amount of health literacy to make the best use of that information. Health literacy means the ability to obtain and comprehend the basic health information to make appropriate health decisions. To build the bridge between this gap, organizations advocate adapting this medical knowledge into plain language. Building robust systems to automate the adaptations helps both medical and non-medical professionals best leverage the available information online. The goal of the Plain Language Adaptation of Biomedical Abstracts (PLABA) track is to adapt the biomedical abstracts in English language extracted from PubMed based on the questions asked in MedlinePlus for the general public using plain language at the sentence level. As part of this track, we leveraged the best open-source Large Language Models suitable and fine-tuned for dialog use cases. We compare and present the results for all of our systems and our ranking among the other participants' submissions. Our top performing GPT-4 based model ranked first in the avg. simplicity measure and 3rd on the avg. accuracy measure.