Activation Addition steers language models by adding contrastive activation vectors from prompt pairs to control high-level properties like sentiment and toxicity at inference time without training.
Controllable text generation via probability density estimation in the latent space
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
OLLM models next-token generation as a latent-indexed set of options, enabling up to 70% math reasoning correctness versus 51% baselines and structure-based alignment via a compact latent policy.
citing papers explorer
-
Steering Language Models With Activation Engineering
Activation Addition steers language models by adding contrastive activation vectors from prompt pairs to control high-level properties like sentiment and toxicity at inference time without training.
-
OLLM: Options-based Large Language Models
OLLM models next-token generation as a latent-indexed set of options, enabling up to 70% math reasoning correctness versus 51% baselines and structure-based alignment via a compact latent policy.