LLM4SR: A Survey on Large Language Models for Scientific Research

TL;DR

This survey reviews how large language models are transforming scientific research by supporting hypothesis generation, experiment planning, writing, and peer review, highlighting methodologies, challenges, and future directions.

Contribution

It provides the first comprehensive overview of LLM applications in scientific research, detailing task-specific methods and evaluation benchmarks across research stages.

Findings

LLMs assist in hypothesis discovery and scientific writing.

Identification of key challenges in applying LLMs to research.

Proposals for future research directions in LLM-driven scientific inquiry.

Abstract

In recent years, the rapid advancement of Large Language Models (LLMs) has transformed the landscape of scientific research, offering unprecedented support across various stages of the research cycle. This paper presents the first systematic survey dedicated to exploring how LLMs are revolutionizing the scientific research process. We analyze the unique roles LLMs play across four critical stages of research: hypothesis discovery, experiment planning and implementation, scientific writing, and peer reviewing. Our review comprehensively showcases the task-specific methodologies and evaluation benchmarks. By identifying current challenges and proposing future research directions, this survey not only highlights the transformative potential of LLMs, but also aims to inspire and guide researchers and practitioners in leveraging LLMs to advance scientific inquiry. Resources are available at the following repository: https://github.com/du-nlp-lab/LLM4SR