Stable-GFlowNet improves training stability and attack diversity in LLM red-teaming by eliminating Z estimation via contrastive trajectory balance while preserving GFN optimality.
Safety Pretraining: Toward the Next Generation of Safe
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
Stable-GFlowNet improves training stability and attack diversity in LLM red-teaming by eliminating Z estimation via contrastive trajectory balance while preserving GFN optimality.