Using a revealed-preference framework, seven of 39 LLMs passed a statistical test of approximately consistent moral choice, and the passing models show both a shared moral core and measurable differences.
Consistency and Heterogeneity of Individual Behavior under Uncertainty
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Moral Mind(s) of Large Language Models
Using a revealed-preference framework, seven of 39 LLMs passed a statistical test of approximately consistent moral choice, and the passing models show both a shared moral core and measurable differences.