LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations
For qualitative researchers, this paper provides practical considerations for integrating LLMs responsibly, but it is primarily a conceptual discussion without empirical results.
This paper explores the opportunities and limitations of using LLMs in qualitative research, arguing that responsible integration requires critical engagement with technical parameters like context windows, sampling settings, and prompt design, while considering epistemological commitments such as reflexivity and interpretive judgment.
This paper examines the opportunities, limitations, and practical considerations associated with the use of large language models (LLMs) in qualitative research. Drawing on a multidisciplinary perspective that combines expertise in qualitative methods and explainable AI, the paper argues that responsible integration of LLMs into qualitative workflows requires researchers to engage critically with a curated set of technical parameters, that is, context window constraints, temperature and top-p sampling settings, user and system prompt design, and model documentation in the form of system cards. The paper situates these considerations within the epistemological commitments of qualitative research, including reflexivity, positionality, and interpretive judgment, and discusses how the opacity of contemporary LLMs differs from earlier natural language processing tools such as topic models and lexicon-based sentiment analyzers.