CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916407800758272 |
|---|---|
| author | Lv, Yaojia Pan, Haojie Wang, Zekun Liang, Jiafeng Liu, Yuanxing Fu, Ruiji Liu, Ming Wang, Zhongyuan Qin, Bing |
| author_facet | Lv, Yaojia Pan, Haojie Wang, Zekun Liang, Jiafeng Liu, Yuanxing Fu, Ruiji Liu, Ming Wang, Zhongyuan Qin, Bing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08438 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models Lv, Yaojia Pan, Haojie Wang, Zekun Liang, Jiafeng Liu, Yuanxing Fu, Ruiji Liu, Ming Wang, Zhongyuan Qin, Bing Computation and Language Artificial Intelligence Machine Learning 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. |
| title | CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.08438 |