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

Abstract

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.

Ähnliche Arbeiten