Qian Niu, Junyu Liu, Ziqian Bi, Pohsun Feng, Benji Peng, Keyu Chen, Ming Li, Lawrence K.Q. Yan, Yichao Zhang, Caitlyn Heqi Yin, Cheng Fei, Tianyang Wang, Yunze Wang, Silin Chen, Ming Liu, Ziyuan Qin, Riyang Bao, Xinyuan Song, ZeKun Jiang
This comprehensive review explores the intersection between large language models (LLMs) and cognitive science, by 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. This review covers applications of LLMs in various cognitive fields and highlights 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, thus 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 understanding of both AI and human intelligence.