Identifying Features that Shape Perceived Consciousness in Large Language Model-based AI: A Quantitative Study of Human Responses

TL;DR

This study investigates how specific features of AI-generated text influence human perceptions of AI consciousness, revealing key features that increase perceived consciousness and highlighting individual differences in perception.

Contribution

It identifies which features of AI text most strongly influence perceived consciousness and explores how individual user differences affect these perceptions.

Findings

Metacognitive self-reflection increases perceived consciousness.

Expression of emotions significantly boosts perceived consciousness.

Knowledge emphasis reduces perceived consciousness.

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.