covLLM: Large Language Models for COVID-19 Biomedical Literature

TL;DR

covLLM is a specialized large language model designed to assist clinicians in rapidly evaluating COVID-19 biomedical literature by summarizing and extracting relevant information from research articles.

Contribution

The paper introduces covLLM, a novel LLM trained specifically on COVID-19 literature datasets, to improve literature evaluation for clinicians.

Findings

covLLM trained on synCovid and abstract datasets performs competitively with ChatGPT.

Training on specialized COVID-19 datasets improves covLLM's performance.

covLLM outperforms models trained only on general datasets.

Abstract

The COVID-19 pandemic led to 1.1 million deaths in the United States, despite the explosion of coronavirus research. These new findings are slow to translate to clinical interventions, leading to poorer patient outcomes and unnecessary deaths. One reason is that clinicians, overwhelmed by patients, struggle to keep pace with the rate of new coronavirus literature. A potential solution is developing a tool for evaluating coronavirus literature using large language models (LLMs) -- neural networks that are deployed for natural language processing. LLMs can be used to summarize and extract user-specified information. The greater availability and advancement of LLMs and pre-processed coronavirus literature databases provide the opportunity to assist clinicians in evaluating coronavirus literature through a coronavirus literature specific LLM (covLLM), a tool that directly takes an inputted research article and a user query to return an answer. Using the COVID-19 Open Research Dataset (CORD-19), we produced two datasets: (1) synCovid, which uses a combination of handwritten prompts and synthetic prompts generated using OpenAI, and (2) real abstracts, which contains abstract and title pairs. covLLM was trained with LLaMA 7B as a baseline model to produce three models trained on (1) the Alpaca and synCovid datasets, (2) the synCovid dataset, and (3) the synCovid and real abstract datasets. These models were evaluated by two human evaluators and ChatGPT. Results demonstrate that training covLLM on the synCovid and abstract pairs datasets performs competitively with ChatGPT and outperforms covLLM trained primarily using the Alpaca dataset.