Emulating Cognitive Style in Large Language Models

Abstract Large Language Models (LLMs) have emerged as a pivotal technology in the evolving world. With respect to design, the significance of LLMs lies in their transformative potential for collaborating design teams. However, it is not known whether LLMs can emulate cognitive and social attributes which are known to be important during design, such as cognitive style. This research evaluates the efficacy of LLMs to emulate aspects of Kirton’s adaption innovation inventory, which characterizes approaches to problem-solving. Specifically, we use LLMs to generate solutions for three design problems using two different cognitive style prompts (adaptive and innovative), and evaluate the solutions with respect to feasibility and paradigm relatedness. We found that solutions generated using the adaptive prompt tend to display higher feasibility and are paradigm preserving, while solutions generated using the innovative prompts were more paradigm modifying. This aligns with prior work and expectations based on KAI theory. Ultimately, these results demonstrate that LLMs can be prompted to accurately emulate cognitive style.