Scientific Computing with Large Language Models

TL;DR

This paper reviews how large language models are transforming scientific computing by enabling natural language processing of scientific texts and specialized languages for biological and physical systems, leading to faster problem solving and system creation.

Contribution

It provides a comprehensive overview of recent applications of large language models in scientific domains, highlighting new use cases and potential for accelerating research.

Findings

Chatbot applications in medicine, mathematics, and physics facilitate iterative problem solving.

Language models predict properties and generate novel biological systems faster than traditional methods.

Use of specialized languages enhances the modeling and understanding of molecular and physical systems.

Abstract

We provide an overview of the emergence of large language models for scientific computing applications. We highlight use cases that involve natural language processing of scientific documents and specialized languages designed to describe physical systems. For the former, chatbot style applications appear in medicine, mathematics and physics and can be used iteratively with domain experts for problem solving. We also review specialized languages within molecular biology, the languages of molecules, proteins, and DNA where language models are being used to predict properties and even create novel physical systems at much faster rates than traditional computing methods.