By comparing activations from trait and neutral prompts, the authors extract a personality direction in Llama 3's Layer 18 and amplify it to steer responses toward that trait.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering
By comparing activations from trait and neutral prompts, the authors extract a personality direction in Llama 3's Layer 18 and amplify it to steer responses toward that trait.