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.
Deep Learning for Text Style Transfer: A Survey
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2verdicts
UNVERDICTED 2representative citing papers
A decoder is trained on 1010 style features to map style representations back to prompts, outperforming direct LLM prompting on style recovery, imitation, and steering tasks.
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.
-
Interpreting Style Representations via Style-Eliciting Prompts
A decoder is trained on 1010 style features to map style representations back to prompts, outperforming direct LLM prompting on style recovery, imitation, and steering tasks.