On-Policy Consistency Training (OPCT) improves LLM safety metrics over supervised fine-tuning while largely preserving capabilities across three model families.
answer” responses, output only a single number for each item. For the “reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
On-Policy Consistency Training (OPCT) improves LLM safety metrics over supervised fine-tuning while largely preserving capabilities across three model families.