Employing large language models in survey research

Abstract

This article discusses the promising potential of employing large language models (LLMs) for survey research, including generating responses to survey items. LLMs can address some of the challenges associated with survey research regarding question-wording and response bias. They can address issues relating to a lack of clarity and understanding but cannot yet correct for sampling or nonresponse bias challenges. While LLMs can assist with some of the challenges with survey research, at present, LLMs need to be used in conjunction with other methods and approaches. With thoughtful and nuanced approaches to development, LLMs can be used responsibly and beneficially while minimizing the associated risks.