Presents a non-linear intervention framework for LLMs with a learning procedure for implicit features, validated on refusal bypass steering showing improved precision over linear baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Non-linear Interventions on Large Language Models
Presents a non-linear intervention framework for LLMs with a learning procedure for implicit features, validated on refusal bypass steering showing improved precision over linear baselines.