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

arXiv: https://arxiv.org/abs/2605.16538 · HTML: https://mlsanity.com/paper/2605.16538/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 58 references that are in the map.
- First posted on arXiv 15 May 2026.

## Builds on (most cited first, 23 of 23)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [The Effect of Sampling Temperature on Problem Solving in Large Language Models](https://mlsanity.com/paper/2402.05201/) (2024)
- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](https://mlsanity.com/paper/2406.06608/) (2024)
- [Generative Language Models Exhibit Social Identity Biases](https://mlsanity.com/paper/2310.15819/) (2023)
- [Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding](https://mlsanity.com/paper/2304.10548/) (2023)
- [Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators](https://mlsanity.com/paper/2307.05532/) (2023)
- [CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models](https://mlsanity.com/paper/2304.07366/) (2023)
- [Artificial Intelligence for Literature Reviews: Opportunities and Challenges](https://mlsanity.com/paper/2402.08565/) (2024)
- [Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs](https://mlsanity.com/paper/2510.01218/) (2025)
- [Thematic Analysis with Open-Source Generative AI and Machine Learning: A New Method for Inductive Qualitative Codebook Development](https://mlsanity.com/paper/2410.03721/) (2024)
- [Inference to the Best Explanation in Large Language Models](https://mlsanity.com/paper/2402.10767/) (2024)
- [Causal Discovery for Explainable AI: A Dual-Encoding Approach](https://mlsanity.com/paper/2601.21221/) (2026)

## Abstract (arXiv)

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.