CogGPT：在大语言模型上释放认知动态的力量
CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models
AI总结：
本文提出LLM认知动态概念及纵向研究任务，开发CogBench基准并引入具有迭代认知机制的CogGPT，以增强终身认知动态，在持续信息流下表现优越。
摘要：
认知动态对于推进人类对世界的理解至关重要。大语言模型（LLMs）的最新进展揭示了其在认知模拟方面的潜力。然而，这些基于LLM的认知研究主要集中于静态建模，忽略了认知的动态本质。为了弥补这一空白，我们提出了LLM的认知动态概念，并在纵向研究的启发下提出了相应的任务。针对该任务，我们开发了CogBench，这是一种用于评估LLM认知动态的新型基准，并通过参与者调查对其进行了验证。我们还为CogBench设计了两个评估指标，包括真实性和合理性。认识到LLM固有的静态特性，我们为该任务引入了CogGPT，其具有创新的迭代认知机制，旨在增强终身认知动态。实证结果表明，CogGPT优于现有方法，特别是在其在持续信息流下促进特定角色认知动态的能力方面。
英文摘要：
Cognitive dynamics are pivotal to advance human understanding of the world. Recent advancements in large language models (LLMs) reveal their potential for cognitive simulation. However, these LLM-based cognitive studies primarily focus on static modeling, overlooking the dynamic nature of cognition. To bridge this gap, we propose the concept of the cognitive dynamics of LLMs and present a corresponding task with the inspiration of longitudinal studies. Towards the task, we develop CogBench, a novel benchmark to assess the cognitive dynamics of LLMs and validate it through participant surveys. We also design two evaluation metrics for CogBench, including Authenticity and Rationality. Recognizing the inherent static nature of LLMs, we introduce CogGPT for the task, which features an innovative iterative cognitive mechanism aimed at enhancing lifelong cognitive dynamics. Empirical results demonstrate the superiority of CogGPT over existing methods, particularly in its ability to facilitate role-specific cognitive dynamics under continuous information flows.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
