Evaluating Explanations Through LLMs: Beyond Traditional User Studies
This offers a potential scalable and cost-effective method for simplifying qualitative XAI evaluation, which is incremental as it applies existing LLMs to a new evaluation task.
The paper tackles the problem of costly and unscalable traditional user studies for evaluating explainable AI (XAI) tools by using Large Language Models (LLMs) to replicate human participants, showing that LLMs can replicate most conclusions from an original study comparing counterfactual and causal explanations.
As AI becomes fundamental in sectors like healthcare, explainable AI (XAI) tools are essential for trust and transparency. However, traditional user studies used to evaluate these tools are often costly, time consuming, and difficult to scale. In this paper, we explore the use of Large Language Models (LLMs) to replicate human participants to help streamline XAI evaluation. We reproduce a user study comparing counterfactual and causal explanations, replicating human participants with seven LLMs under various settings. Our results show that (i) LLMs can replicate most conclusions from the original study, (ii) different LLMs yield varying levels of alignment in the results, and (iii) experimental factors such as LLM memory and output variability affect alignment with human responses. These initial findings suggest that LLMs could provide a scalable and cost-effective way to simplify qualitative XAI evaluation.