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

Summary

Argues that responsibly folding LLMs into qualitative workflows requires researchers to engage explicitly with technical parameters - context window limits, temperature and top-p, user and system prompt design, model system cards - and situates these inside the epistemological commitments of qualitative research (reflexivity, positionality, interpretive judgement). Notes that LLM opacity differs in kind from earlier NLP tools like topic models and lexicon sentiment analysers. A practical methods reference for the qualitative side of IS research pipelines.

Contribution

Queued — not yet read.

Method

Queued — not yet read.

Relevance to RISE

Surfaced by the 2026-08-29 literature sweep as a medium-priority candidate for the RISE knowledge base (angle: human–AI research collaboration). Verified against: arXiv abstract page opened 2026-08-29 (title, 4 authors, submitted 15 May 2026, ASEE 2026 venue note and full abstract read)

Critique / open questions

Queued — not yet assessed.

Key quotes

This paper examines the opportunities, limitations, and practical considerations associated with the use of large language models (LLMs) in qualitative research. (abstract)

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. (abstract)