Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks
Sirui Chen, Shuqin Ma, Shu Yu, Hanwang Zhang, Shengjie Zhao, Chaochao Lu
arXiv Preprint Archive May 26, 2025 Peer reviewed via arXiv
Summary
As AI language models grow more sophisticated, researchers are tackling a fascinating question: could these systems develop consciousness? New findings in computational linguistics (cs.CL) and machine learning (cs.LG) suggest that while today's AI shows signs of awareness, it's fundamentally different from human consciousness. The study examines social impact (cs.CY) and potential risks, concluding that AI exhibits complex behaviors without true consciousness.
Abstract
Consciousness stands as one of the most profound and distinguishing features of the human mind, fundamentally shaping our understanding of existence and agency. As large language models (LLMs) develop at an unprecedented pace, questions concerning intelligence and consciousness have become increasingly significant. However, discourse on LLM consciousness remains largely unexplored territory. In this paper, we first clarify frequently conflated terminologies (e.g., LLM consciousness and LLM awareness). Then, we systematically organize and synthesize existing research on LLM consciousness from both theoretical and empirical perspectives. Furthermore, we highlight potential frontier risks that conscious LLMs might introduce. Finally, we discuss current challenges and outline future directions in this emerging field. The references discussed in this paper are organized at https://github.com/OpenCausaLab/Awesome-LLM-Consciousness.