A reporting checklist for large language models in behavioural science

Researchers have introduced a consensus-based reporting checklist called GUIDE-LLM to improve the transparency and reproducibility of studies using large language models in behavioral science. The guidelines aim to address the challenges posed by the rapid evolution of AI tools in academic research.
Why it matters
Standardizing AI usage in research is critical for maintaining scientific rigor and ethical accountability in social science.
Nature Human Behaviour ( 2026 ) Cite this article
The article is a factual report on academic standards and methodology.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in