Framework-Based Qualitative Analysis of Free Responses of Large Language Models: Algorithmic Fidelity
This work addresses the validity of using LLMs in qualitative research for social scientists, highlighting an incremental step by applying existing methods to a new context with cautionary findings.
The study assessed whether large language models (LLMs) can simulate human-like free responses for qualitative research by evaluating algorithmic fidelity, finding that GPT-3.5 showed similar key themes but significant differences in structure and tone, indicating insufficient fidelity for generalization to human populations.
Today, using Large-scale generative Language Models (LLMs) it is possible to simulate free responses to interview questions like those traditionally analyzed using qualitative research methods. Qualitative methodology encompasses a broad family of techniques involving manual analysis of open-ended interviews or conversations conducted freely in natural language. Here we consider whether artificial "silicon participants" generated by LLMs may be productively studied using qualitative methods aiming to produce insights that could generalize to real human populations. The key concept in our analysis is algorithmic fidelity, a term introduced by Argyle et al. (2023) capturing the degree to which LLM-generated outputs mirror human sub-populations' beliefs and attitudes. By definition, high algorithmic fidelity suggests latent beliefs elicited from LLMs may generalize to real humans, whereas low algorithmic fidelity renders such research invalid. Here we used an LLM to generate interviews with silicon participants matching specific demographic characteristics one-for-one with a set of human participants. Using framework-based qualitative analysis, we showed the key themes obtained from both human and silicon participants were strikingly similar. However, when we analyzed the structure and tone of the interviews we found even more striking differences. We also found evidence of the hyper-accuracy distortion described by Aher et al. (2023). We conclude that the LLM we tested (GPT-3.5) does not have sufficient algorithmic fidelity to expect research on it to generalize to human populations. However, the rapid pace of LLM research makes it plausible this could change in the future. Thus we stress the need to establish epistemic norms now around how to assess validity of LLM-based qualitative research, especially concerning the need to ensure representation of heterogeneous lived experiences.