Personality-prompted LLMs do not reliably behave in line with the ascribed Big Five traits in Ultimatum Game and Milgram-style tests, with trends sometimes reversing human patterns.
As shown in the baseline plots (Fig
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
-
Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?
Personality-prompted LLMs do not reliably behave in line with the ascribed Big Five traits in Ultimatum Game and Milgram-style tests, with trends sometimes reversing human patterns.