将大模型比作人类直觉，提出双进程架构可提升其认知能力。
Roles of LLMs in the Overall Mental Architecture
- 把大模型类比为人类隐性认知过程，如直觉与本能。
- 提出双进程框架可融合显性符号处理与隐性生成，实现协同增强。
- 适合关注认知科学与AI融合的研究者参考。
为了更好地理解现有大语言模型（LLMs），可以借鉴人类心理（认知/心理学）架构及其组成部分与结构。基于心理学、哲学和认知科学文献，认为在人类心理架构中，现有大模型与隐性心理过程（如直觉、本能等）高度对应。然而，从心理学、哲学和认知科学角度观察，人类心智架构中还存在显性过程（具备更强的符号处理能力）。本文探讨了相关理论与实证问题。进一步主张，现有的双进程计算认知架构（模拟人类认知/心理架构的模型）为从根本上增强大模型提供了可用框架——通过引入隐性和显性双进程；同时，这些架构也可被大模型所增强。结果是多种意义上协同组合的增益。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。