Mean-difference residual stream injections outperform personality prompting for OCEAN trait steering in most LLMs, with hybrids performing best and showing approximate linearity but non-human trait covariances.
Moral foun- dations vignettes: A standardized stimulus database of scenarios based on moral foundations theory.Behavior research methods, 47(4):1178–1198, 2015
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Psychological Steering of Large Language Models
Mean-difference residual stream injections outperform personality prompting for OCEAN trait steering in most LLMs, with hybrids performing best and showing approximate linearity but non-human trait covariances.