Dual Process Theory

Dual process theory posits that human cognition operates through two interacting systems: a fast, intuitive System 1 and a slower, deliberative System 2. Current research explores how this framework applies to artificial intelligence, particularly large language models (LLMs), investigating how prompting techniques can influence the balance between these systems and mitigate biases in LLM outputs. This research leverages various model architectures, including attention-based mechanisms and rule-controllable decoding strategies, to better understand and potentially improve the efficiency and ethical implications of AI systems. The insights gained are significant for advancing both cognitive science and the development of more human-like and less biased AI.