Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Do LLMs have Consistent Values?
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-103
LLMs' value rankings align with the universal human value hierarchy under most prompting conditions
IC-104
Value anchor prompting produces LLM value correlation structures that closely match the human circular value structure, while standard prompting does not
IC-105
Value anchoring produces a sinusoidal scoring pattern around the circular value structure, with scores decreasing as circular distance from the anchor increases