Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909623262380032 |
|---|---|
| author | Chen, Sirui Ma, Shuqin Yu, Shu Zhang, Hanwang Zhao, Shengjie Lu, Chaochao |
| author_facet | Chen, Sirui Ma, Shuqin Yu, Shu Zhang, Hanwang Zhao, Shengjie Lu, Chaochao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19806 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks Chen, Sirui Ma, Shuqin Yu, Shu Zhang, Hanwang Zhao, Shengjie Lu, Chaochao Computation and Language Computers and Society Machine Learning 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. |
| title | Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks |
| topic | Computation and Language Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2505.19806 |