Enhancing Biosecurity with Language Models: Defining Research Directions

11 Pages Posted: 15 Apr 2024

See all articles by Michael Chen

Michael Chen

Independent

Martin Holub

Delft University of Technology - Department of Bionanoscience

Cameron Tice

Auburn University

Date Written: March 25, 2024

Abstract

This report explores the potential of large language models (LLMs) to enhance biosecurity. We conducted interviews with nine biosecurity experts to understand their daily tasks, and how LLMs could be more useful for their work. Our findings indicate that approximately 50% of our interviewees’ biosecurity-related tasks, such as gathering information from papers and reports, reviewing safety forms, and writing memos and summaries, have high potential for automation with LLMs. Skills critical for biosecurity work, like processing information and communicating effectively, could also be augmented by LLMs. However, current LLMs have limitations, such as often providing shallow or incorrect information. We provide suggestions for LLM-based tools that could significantly advance biosecurity efforts and list field-specific datasets to facilitate their development.

Keywords: biosecurity, AI, large language models

Suggested Citation

Chen, Michael and Holub, Martin and Tice, Cameron, Enhancing Biosecurity with Language Models: Defining Research Directions (March 25, 2024). Available at SSRN: https://ssrn.com/abstract=4772574 or http://dx.doi.org/10.2139/ssrn.4772574

Martin Holub

Delft University of Technology - Department of Bionanoscience ( email )

Netherlands

Cameron Tice

Auburn University ( email )

415 West Magnolia Avenue
Auburn, AL 36849
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
26
Abstract Views
223
PlumX Metrics