Distorted Perspectives of LLM-Simulated Preferences: Can AI Mislead Design?

TL;DR

This study examines how LLM-simulated design preferences differ from real user preferences, revealing systematic discrepancies and highlighting limitations in current LLM simulation practices for design tasks.

Contribution

It provides empirical evidence of the misalignment between LLM-driven simulations and actual user preferences in visual design, emphasizing the need for improved simulation methods.

Findings

Significant discrepancies between real and simulated preferences.

Synthetic justifications lack depth and nuance.

Lack of alignment persists across various LLM configurations.

Abstract

Designers of digital solutions increasingly consult Large Language Models (LLMs) for their work. However, it remains unclear how this may affect the user experiences they produce and there are no established practices. We investigate how design preferences expressed by LLM-driven simulation methods align with those of real users. We present a study that aggregates real-world data and design stimuli from twenty-nine preference tests conducted in practice by users of the UXtweak online research platform (n = 2073). We perform holistic multimodal simulations where we manipulate LLM variables (model reasoning, sampling, persona type, and specificity) and assess their effects on algorithmic fidelity. Our results unveil significant and systematic discrepancies between peoples' real design preferences and LLM simulations that are consistent across manipulations. Synthetic justifications lack genuine depth, nuance and reasoning, which they substitute by patterns like focus on generic properties, specific elements, elaboration and overpraising. The unique attention directed by this research toward preferences within visual design stimuli highlights misrepresentation of perception and meaning by LLMs in a context that is intuitive yet critical for design teams. The external and ecological validity of our findings is high, given their replication across a multitude of real-world studies.