Harnessing large language models for coding, teaching and inclusion to empower research in ecology and evolution

作者：Natalie Cooper, Adam Thomas Clark, Nicolas Lecomte, Huijie Qiao, Aaron M. Ellison · 发表于：Methods in Ecology and Evolution · 年份：2024 · DOI：10.1111/2041-210x.14325 · 被引用次数：31 · 研究领域：Explainable Artificial Intelligence (XAI)、Artificial Intelligence in Healthcare and Education、Machine Learning in Materials Science

Abstract Large language models (LLMs) are a type of artificial intelligence (AI) that can perform various natural language processing tasks. The adoption of LLMs has become increasingly prominent in scientific writing and analyses because of the availability of free applications such as ChatGPT. This increased use of LLMs not only raises concerns about academic integrity but also presents opportunities for the research community. Here we focus on the opportunities for using LLMs for coding in ecology and evolution. We discuss how LLMs can be used to generate, explain, comment, translate, debug, optimise and test code. We also highlight the importance of writing effective prompts and carefully evaluating the outputs of LLMs. In addition, we draft a possible road map for using such models inclusively and with integrity. LLMs can accelerate the coding process, especially for unfamiliar tasks, and free up time for higher level tasks and creative thinking while increasing efficiency and creative output. LLMs also enhance inclusion by accommodating individuals without coding skills, with limited access to education in coding, or for whom English is not their primary written or spoken language. However, code generated by LLMs is of variable quality and has issues related to mathematics, logic, non‐reproducibility and intellectual property; it can also include mistakes and approximations, especially in novel methods. We highlight the benefits of using LLMs to teach and learn coding, ...