Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks

TL;DR

This paper systematically reviews theories, implementations, and risks related to consciousness in large language models, clarifying terminology and highlighting future research challenges in this emerging field.

Contribution

It provides a comprehensive organization and synthesis of existing research on LLM consciousness, including theoretical, empirical, and risk perspectives, which is largely unexplored.

Findings

Clarification of key terminologies like LLM consciousness and awareness

Organization of existing research from theoretical and empirical viewpoints

Identification of potential frontier risks associated with conscious LLMs

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.