Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs
2024-01-16
· ICLR 2024 oral ·
anchor
Findings
IC-827
LLMs exhibit distinct psychological profiles that differ from human norms and vary by model size and version
IC-828
Jailbreaking GPT-4 via cipherchat shifts its psychological profile toward human norms and reduces emotional intelligence scores
IC-829
Role assignment to GPT-3.5-turbo produces role-consistent changes in psychological profiles and task performance, validating the psychometric scales