LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations

TL;DR

This paper explores how large language models can be responsibly integrated into qualitative research, emphasizing technical, epistemological, and interpretive considerations for effective use.

Contribution

It provides a multidisciplinary analysis of opportunities and limitations of LLMs in qualitative research, highlighting practical guidelines and critical engagement with technical parameters.

Findings

LLMs offer new opportunities for qualitative analysis.

Responsible use requires understanding technical and epistemological factors.

Opacity of LLMs differs from earlier NLP tools, affecting interpretive judgment.

Abstract

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.