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.
The power of scale for parameter-efficient prompt tuning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
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.