Roles of LLMs in the Overall Mental Architecture
This work addresses the integration of cognitive science insights into AI development for researchers and practitioners, but it is incremental as it builds on existing dual-process theories without presenting new empirical results.
The paper examines how existing large language models (LLMs) align with implicit mental processes in human cognition, such as intuition, and argues that incorporating explicit processes, like symbolic capabilities, from dual-process cognitive architectures can fundamentally enhance LLMs, leading to synergistic combinations.
To better understand existing LLMs, we may examine the human mental (cognitive/psychological) architecture, and its components and structures. Based on psychological, philosophical, and cognitive science literatures, it is argued that, within the human mental architecture, existing LLMs correspond well with implicit mental processes (intuition, instinct, and so on). However, beyond such implicit processes, explicit processes (with better symbolic capabilities) are also present within the human mental architecture, judging from psychological, philosophical, and cognitive science literatures. Various theoretical and empirical issues and questions in this regard are explored. Furthermore, it is argued that existing dual-process computational cognitive architectures (models of the human cognitive/psychological architecture) provide usable frameworks for fundamentally enhancing LLMs by introducing dual processes (both implicit and explicit) and, in the meantime, can also be enhanced by LLMs. The results are synergistic combinations (in several different senses simultaneously).