Prompt-based steering outperformed activation-based steering on accuracy, but no method produced representations well aligned with human judgments, especially for size.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating Steering Techniques using Human Similarity Judgments
Prompt-based steering outperformed activation-based steering on accuracy, but no method produced representations well aligned with human judgments, especially for size.