MLLMs as Human Surrogates for Explainable AI Evaluation
This paper investigates whether multimodal large language models can act as surrogate human participants to automate the evaluation of explainable AI techniques. It proposes a purpose-grounded evaluation framework with metrics applicable to both MLLMs and human users, and offers conceptual arguments for when such automation can be trusted. Empirical testing covers five purpose-grounded areas and fourteen popular MLLMs, finding that all models trend positively while OpenAI and Qwen variants generally show higher alignment. The authors present the approach as a complement to, not a replacement for, user testing.