Table 1 Correlations between ChatGPT model predictions and human judgments for current stimuli.

From: ChatGPT does not replicate human moral judgments: the importance of examining metrics beyond correlation to assess agreement

Correlation pair

Combined

Human-authored

GPT-authored

davinci-003—human

r = 0.98

r = 0.98

r = 0.98

GPT-4o—human

r = 0.98

r = 0.99

r = 0.98

Back to article page