Identifying Features that Shape Perceived Consciousness in Large Language Model-based AI: A Quantitative Study of Human Responses
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingLarge Language ModelLogical ReasoningSimilar Papers 제목 키워드 기반
AI and Consciousness: Shifting Focus Towards Tractable Questions
As language-based AI systems become more anthropomorphic, the question of whether they can have subjective experience is increasingly pressing. I focus here on the tractability of research questions in the space of AI co…
The Morphospace of Consciousness
We construct a complexity-based morphospace to study systems-level properties of conscious & intelligent systems. The axes of this space label 3 complexity types: autonomous, cognitive & social. Given recent proposals to…
Synaptic clock as a neural substrate of consciousness
In this theoretical work the temporal aspect of consciousness is analyzed. We start from the notion that while conscious experience seems to change constantly, yet for any of its contents to be consciously perceived they…
Perceived AGI: Believability as Dimensional Completeness, Not Capability
Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind. We hypothesize that a central missing ingr…
Identifying Emotions from Walking using Affective and Deep Features
We present a new data-driven model and algorithm to identify the perceived emotions of individuals based on their walking styles. Given an RGB video of an individual walking, we extract his/her walking gait in the form o…
Emotion Recognition