Contrastive Activation Addition steers Llama 2 Chat by adding averaged residual-stream activation differences from contrastive example pairs to control targeted behaviors at inference time.
Transfer Learning Improves F rench Cross-Domain Dialect Identification: NRC @ V ar D ial 2022
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 Llama 2 via Contrastive Activation Addition
Contrastive Activation Addition steers Llama 2 Chat by adding averaged residual-stream activation differences from contrastive example pairs to control targeted behaviors at inference time.