MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
This addresses the resource constraints in early UI design exploration for designers by supplementing user research, though it is incremental in applying existing MLLMs to a new domain.
The paper tackled the problem of predicting human perception of user interfaces using multimodal large language models (MLLMs) as early evaluators, finding that MLLMs approximate human preferences on some dimensions but diverge on others, with results based on benchmarking across 30 interfaces.
In an ideal design pipeline, user interface (UI) design is intertwined with user research to validate decisions, yet studies are often resource-constrained during early exploration. Recent advances in multimodal large language models (MLLMs) offer a promising opportunity to act as early evaluators, helping designers narrow options before formal testing. Unlike prior work that emphasizes user behavior in narrow domains such as e-commerce with metrics like clicks or conversions, we focus on subjective user evaluations across varied interfaces. We investigate whether MLLMs can mimic human preferences when evaluating individual UIs and comparing them. Using data from a crowdsourcing platform, we benchmark GPT-4o, Claude, and Llama across 30 interfaces and examine alignment with human judgments on multiple UI factors. Our results show that MLLMs approximate human preferences on some dimensions but diverge on others, underscoring both their potential and limitations in supplementing early UX research.