Xu, Evans map four LLM roles across social sciences

A new review in Nature Human Behaviour argues large language models now occupy four distinct research roles in computational social science: subjects that simulate human behaviour, assistants that automate analysis, collaborators that generate hypotheses, and evaluators that audit and improve research quality.

The paper is led by Fengli Xu and James Evans, with co-authors surveying work across sociology, political science, psychology, anthropology, economics and related fields. They describe how LLMs "accelerate discovery while creating new methodological paradigms" at a moment when "society itself becomes saturated with artificial intelligence agents."

The judgment the review itself delivers is restrained. LLMs "struggle with causal inference and raise urgent ethical concerns about privacy and misinformation," the authors write, and their "ability to reproduce social complexity remains uneven and unproven."

The paper closes by pointing to "critical research directions for harnessing LLMs' potential while addressing their limitations."