SteeringDiffusion supplies a bottlenecked, prompt-conditioned activation interface for frozen diffusion models that delivers smooth monotonic content-style control via one runtime scalar and timestep gating.
Locating and editing factual associations in gpt
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Sentiment is represented as a single linear direction in LLM activation space that is causally relevant across tasks and is summarized at punctuation and names in addition to charged words.
citing papers explorer
-
SteeringDiffusion: A Bottlenecked Activation Control Interface for Diffusion Models
SteeringDiffusion supplies a bottlenecked, prompt-conditioned activation interface for frozen diffusion models that delivers smooth monotonic content-style control via one runtime scalar and timestep gating.
-
Linear Representations of Sentiment in Large Language Models
Sentiment is represented as a single linear direction in LLM activation space that is causally relevant across tasks and is summarized at punctuation and names in addition to charged words.