Value-prompted LLMs align with human value structures and value-behavior relationships, and incorporating human value distributions improves population-level simulations.
It is important to him/her to take care of people he/she is close to
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
Value-prompted LLMs align with human value structures and value-behavior relationships, and incorporating human value distributions improves population-level simulations.