CAST transfers knowledge across tasks by adding the average few-shot minus zero-shot activation difference from a high-resource task to a low-resource task's hidden state, improving accuracy without training or longer prompts.
Spot: Better frozen model adaptation through soft prompt transfer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Enhancing Cross-task Transfer of Large Language Models via Activation Steering
CAST transfers knowledge across tasks by adding the average few-shot minus zero-shot activation difference from a high-resource task to a low-resource task's hidden state, improving accuracy without training or longer prompts.