Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges
Qian Niu, Junyu Liu, Ziqian Bi, Pohsun Feng, Benji Peng, Keyu Chen, Ming Li, Lawrence KQ Yan, Yichao Zhang, Caitlyn Heqi Yin, Cheng Fei, Tianyang Wang, Yunze Wang, Silin Chen, Ming Liu, Ziyuan Qin, Riyang Bao, Xinyuan Song, Zekun Jiang
TL;DR
The paper surveys how Large Language Models relate to cognitive science, comparing shared abilities and gaps in reasoning, memory, and representation. It reviews evaluation methods and presents LLMs as cognitive models and research tools, while highlighting biases and the need for careful interpretation. It discusses applications in causal reasoning, semantics, and creative tasks, as well as integration with cognitive architectures. The work outlines future directions for aligning LLMs with human cognition, improving domain-specific performance, and advancing interdisciplinary methods for robust, ethical AI-assisted cognitive science.
Abstract
This comprehensive review explores the intersection of Large Language Models (LLMs) and cognitive science, examining similarities and differences between LLMs and human cognitive processes. We analyze methods for evaluating LLMs cognitive abilities and discuss their potential as cognitive models. The review covers applications of LLMs in various cognitive fields, highlighting insights gained for cognitive science research. We assess cognitive biases and limitations of LLMs, along with proposed methods for improving their performance. The integration of LLMs with cognitive architectures is examined, revealing promising avenues for enhancing artificial intelligence (AI) capabilities. Key challenges and future research directions are identified, emphasizing the need for continued refinement of LLMs to better align with human cognition. This review provides a balanced perspective on the current state and future potential of LLMs in advancing our understanding of both artificial and human intelligence.