Ten simple rules for using large language models in science, version 1.0

• DOI: 10.1371/journal.pcbi.1011767
• Publication Date: 2024-01-31T18:36:58Z
• Authors: Gabriel Reuben Smith; Carolina Bello; Lalasia Bialic-Mu...; Emily Clark; Camille S. Delavaux; Camille Fournier ...; Johan van den Hoogen; Thomas Lauber; Haozhi Ma; Daniel S. Maynard; Matthew Mirman; Lidong Mo; Dominic Rebindaine; Josephine Elena Reek; Leland K. Werden; Zhaofei Wu; Gayoung Yang; Qingzhou Zhao; Constantin M. Zohner; Thomas W. Crowther
• Keywords: Carbon sequestration; QH301-705.5; Science; Conservation science; Scientists; Climate change; Biodiversity; Biodiversity; Language; Forests; Trees; Conservation science; Scientists; Carbon sequestration; Climate change; Biology (General); Forests; Education; Language; Trees

Box 1-An LLM suggests 10 simple rules governing its own usage in scienceHere, we ask ChatGPT to generate a list of for using LLMs science order illustrate ability provide detailed, human-like responses short prompts. Q1:Can you me with ten large language models science?R1 (ChatGPT 3.5): Certainly!Here are science:1. Understand the limitations: Recognize that like GPT-3 powerful but not infallible.They may produce accurate-sounding information, they can also false or biased content.Exercise caution and critical thinking.2. Validate verify: Always cross-reference information generated by reliable sources.Verify accuracy claims, check