A decoding-time method called TSDI estimates and removes the context-free refusal bias caused by safety alignment, improving helpfulness while keeping safety.
Deep reinforcement learning from human preferences
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
-
Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing
A decoding-time method called TSDI estimates and removes the context-free refusal bias caused by safety alignment, improving helpfulness while keeping safety.