Fine-tuning LLMs on essays reduces variance in IPIP-NEO responses across models but does not raise full five-trait profile accuracy above near-chance levels from unguided text.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Applies sparse autoencoders to locate and steer latent features for OCEAN personality traits in LLMs while preserving benchmark performance.
citing papers explorer
-
Evaluation Drift in LLM Personality Induction: Are We Moving the Goalpost?
Fine-tuning LLMs on essays reduces variance in IPIP-NEO responses across models but does not raise full five-trait profile accuracy above near-chance levels from unguided text.
-
Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions
Applies sparse autoencoders to locate and steer latent features for OCEAN personality traits in LLMs while preserving benchmark performance.