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.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
MixSD mixes tokens from the base model's expert and naive conditionals to create distribution-aligned supervision for knowledge injection, yielding better memorization-retention trade-offs than SFT across scales and benchmarks.
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.
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.
-
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection
MixSD mixes tokens from the base model's expert and naive conditionals to create distribution-aligned supervision for knowledge injection, yielding better memorization-retention trade-offs than SFT across scales and benchmarks.
-
Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression
LightEdit enables scalable lifelong knowledge editing in LLMs via selective knowledge retrieval and probability suppression during decoding, outperforming prior methods on ZSRE, Counterfact, and RIPE while reducing training costs.