Nature review: LLMs now fill four roles in social science

Large language models in social science now fill four distinct research roles: subjects that simulate human behaviour, assistants that automate analysis, collaborators that generate hypotheses, and evaluators that audit research quality. That is the central framing of a review in Nature Human Behaviour by Fengli Xu, James Evans and colleagues.

The authors frame the moment plainly: 'This transformation arrives as society itself becomes saturated with artificial intelligence agents—making LLMs both our research tools and authentic research subjects.'

Then the limits. 'LLMs struggle with causal inference and raise urgent ethical concerns about privacy and misinformation, and their ability to reproduce social complexity remains uneven and unproven,' the review states. No per-task benchmark numbers or named models appear in the abstract; those sit inside the full text.

The authors frame their field's dilemma as recursive: understanding how AI is reshaping society 'requires the very tools driving it—a recursive challenge that will define the future of social science.' Two researchers we track at AI Weekly shared the paper's link in our directory.