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 preprint
Study at a glance
AI-extracted from the abstract| Characteristics | Review |
|---|---|
| Keywords | Artificial-intelligence Consciousness-and-ai Machine-learning cs.lg Computational-linguistics cs.cl Societal-impact cs.cy |
| Key findings | The paper organizes and synthesizes existing research on LLM consciousness, clarifies terminology, and identifies risks and future directions. |
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.