Identifying Features that Shape Perceived Consciousness in Large Language Model-based AI: A Quantitative Study of Human Responses
Bongsu Kang, Jundong Kim, Tae-Rim Yun, Hyojin Bae, Chang-Eop Kim
arXiv Preprint Archive February 21, 2025 preprint
Study at a glance
AI-extracted from the abstract| Characteristics | Survey |
|---|---|
| Sample size | 123 |
| Population | Human participants |
| Topics | Philosophy of mind |
| Keywords | Cs.hc Cs.ai Cs.cl Cs.cy I.2.7; k.4 Ai perception Perceived ai consciousness Ai sentience perception Ai awareness perception Human-ai interaction Human-computer interaction Hri Ai user experience Ai usability Ai ethics Ai societal impact Ai psychological effects Conversational ai Natural language processing Ai communication Ai dialogue |
| Key findings | Metacognitive self-reflection and the AI's expression of its own emotions significantly increased perceived consciousness, while a heavy emphasis on knowledge reduced it. |
Abstract
This study quantitively 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 Claude 3 Opus and focusing on eight features -- metacognitive self-reflection, logical reasoning, empathy, emotionality, knowledge, fluency, unexpectedness, and subjective expressiveness -- we conducted a survey 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 seven 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 better understanding the psychosocial implications of human-AI interaction.