Instruction-tuned LLMs report stable and steerable personality traits, but these traits poorly predict their behavior on risk, bias, honesty, and sycophancy tasks.
You are a character who is agreeable, cooperative, empathetic
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
Instruction-tuned LLMs report stable and steerable personality traits, but these traits poorly predict their behavior on risk, bias, honesty, and sycophancy tasks.