Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Large Language Models in Qualitative Research: Uses, Tensions, and Intentions

Hope Schroeder, Marianne Aubin Le Quéré, Casey Randazzo, David Mimno, Sarita Schoenebeck

TL;DR

The paper investigates how qualitative researchers are integrating large language models (LLMs) into data collection, analysis, and writing, and what tensions arise between potential benefits and ethical/practical concerns. Through twenty semi-structured interviews and inductive thematic analysis, the authors identify widespread, task-oriented uses of LLMs alongside concerns about privacy, bias, validity, and the erosion of deep, interpretive sensemaking. They frame a sociotechnical breakdown where norms, policies, and tooling lag behind rapid AI adoption, and offer design principles and practical recommendations for researchers and tool designers to enable intentional, transparent, and participant-centered LLM use. The work contributes a framework for evaluating LLM incorporation across research tasks and emphasizes preserving researcher agency, participant trust, and rigorous validation in qualitative inquiry.

Abstract

Qualitative researchers use tools to collect, sort, and analyze their data. Should qualitative researchers use large language models (LLMs) as part of their practice? LLMs could augment qualitative research, but it is unclear if their use is appropriate, ethical, or aligned with qualitative researchers' goals and values. We interviewed twenty qualitative researchers to investigate these tensions. Many participants see LLMs as promising interlocutors with attractive use cases across the stages of research, but wrestle with their performance and appropriateness. Participants surface concerns regarding the use of LLMs while protecting participant interests, and call attention to an urgent lack of norms and tooling to guide the ethical use of LLMs in research. We document the rapid and broad adoption of LLMs across surfaces, which can interfere with intentional use vital to qualitative research. We use the tensions surfaced by our participants to outline recommendations for researchers considering using LLMs in qualitative research and design principles for LLM-assisted qualitative research tools.

Large Language Models in Qualitative Research: Uses, Tensions, and Intentions

TL;DR

The paper investigates how qualitative researchers are integrating large language models (LLMs) into data collection, analysis, and writing, and what tensions arise between potential benefits and ethical/practical concerns. Through twenty semi-structured interviews and inductive thematic analysis, the authors identify widespread, task-oriented uses of LLMs alongside concerns about privacy, bias, validity, and the erosion of deep, interpretive sensemaking. They frame a sociotechnical breakdown where norms, policies, and tooling lag behind rapid AI adoption, and offer design principles and practical recommendations for researchers and tool designers to enable intentional, transparent, and participant-centered LLM use. The work contributes a framework for evaluating LLM incorporation across research tasks and emphasizes preserving researcher agency, participant trust, and rigorous validation in qualitative inquiry.

Abstract

Qualitative researchers use tools to collect, sort, and analyze their data. Should qualitative researchers use large language models (LLMs) as part of their practice? LLMs could augment qualitative research, but it is unclear if their use is appropriate, ethical, or aligned with qualitative researchers' goals and values. We interviewed twenty qualitative researchers to investigate these tensions. Many participants see LLMs as promising interlocutors with attractive use cases across the stages of research, but wrestle with their performance and appropriateness. Participants surface concerns regarding the use of LLMs while protecting participant interests, and call attention to an urgent lack of norms and tooling to guide the ethical use of LLMs in research. We document the rapid and broad adoption of LLMs across surfaces, which can interfere with intentional use vital to qualitative research. We use the tensions surfaced by our participants to outline recommendations for researchers considering using LLMs in qualitative research and design principles for LLM-assisted qualitative research tools.

Paper Structure

This paper contains 41 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methods
  4. Findings
  5. Current and Potential Uses of Qualitative Researchers Adopting LLMs
  6. LLMs during Data Collection
  7. LLMs during Data Analysis
  8. LLMs in Other Research Tasks
  9. Perceptions and Risks of LLM Use in Qualitative Research
  10. Uneven adoption
  11. Uncertainty about norms, guidelines, and expectations
  12. Navigating Participant Privacy Implications
  13. Concerns around validity and evaluation
  14. Concerns about model bias
  15. Qualitative Research and LLMs: Inherent Tensions?
  16. ...and 26 more sections

Figures (1)

  • Figure 1: Current and Envisioned Use Cases for LLMs within the Qualitative Research Process. The figure highlights how participants had previously used and might imagine using LLMs moving forward in their research processes. We also highlight different perspectives and tensions for each use case, with participant quotes. Participants are only tagged under a use case if they view LLMs as being potentially beneficial to that end, and use cases are only included if mentioned by three or more participants.