Identifying features that shape perceived consciousness in LLM-based AI: A quantitative study of human responses

초록

This study quantitatively examines which features of AI-generated text lead humans to perceive subjective consciousness in large language model (LLM)-based AI systems. Drawing on 99 passages from conversations with AI and focusing on eight features-Metacognitive Self-reflection, Logical Reasoning, Empathy, Emotionality, Knowledge, Fluency, Unexpectedness, and Subjective Expressiveness-we surveyed with 123 participants. Using regression and clustering analyses, we investigated how these features influence participants' perceptions of AI consciousness. The results reveal that metacognitive self-reflection and the AI's expression of its own emotions significantly increased perceived consciousness, while a heavy emphasis on knowledge reduced it. Participants clustered into subgroups, each showing distinct feature-weighting patterns. Additionally, higher prior knowledge of LLMs and more frequent usage of LLM-based chatbots were associated with greater overall likelihood assessments of AI consciousness. This study underscores the multidimensional and individualized nature of perceived AI consciousness and provides a foundation for a better understanding of the psychosocial implications of human-AI interaction.

키워드