ProCon anchors each sample's hidden-state projection onto the LLM's initial refusal direction during instruction fine-tuning, reducing refusal-direction drift and safety risks with limited task-performance loss.
Lisa: Lazy safety alignment for large language models against harmful fine-tuning at- tack,
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
-
Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint
ProCon anchors each sample's hidden-state projection onto the LLM's initial refusal direction during instruction fine-tuning, reducing refusal-direction drift and safety risks with limited task-performance loss.