Systematic experiments reveal that activation steering trades fluency for concept control, is less effective on instruction-tuned models, and that prompting/SFT excel at injection but not removal, with textual metrics correlating to LLM judges.
arXiv preprint arXiv:2406.00244 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Activation steering produces synthetic safety-violating data that improves downstream classifiers over prompting on most tested concepts when a harmonic mean of alignment, coherence, and diversity is optimized.
citing papers explorer
-
On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
Systematic experiments reveal that activation steering trades fluency for concept control, is less effective on instruction-tuned models, and that prompting/SFT excel at injection but not removal, with textual metrics correlating to LLM judges.