@HuggingPapers: Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance Naver AI eliminates unsta…

X AI KOLs Following Papers

Summary

Naver AI introduces Stable-GFlowNet, a method to improve LLM red-teaming by eliminating unstable partition function estimation in Generative Flow Networks through contrastive trajectory balance.

Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance Naver AI eliminates unstable partition function estimation in Generative Flow Networks via pairwise comparisons and robust masking, preventing mode collapse while maintaining diverse https://t.co/xRXREBVzmu
Original Article
View Cached Full Text

Cached at: 05/09/26, 08:16 PM

Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance

Naver AI eliminates unstable partition function estimation in Generative Flow Networks via pairwise comparisons and robust masking, preventing mode collapse while maintaining diverse https://t.co/xRXREBVzmu

Similar Articles

Generating Attacks for LLMs with GFlowNets

arXiv cs.AI

This paper proposes using GFlowNets to train an attacker LLM that automatically generates adversarial attacks against victim LLMs, enabling automated red teaming and robustness scoring in both English and Turkish.

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

Hugging Face Daily Papers

LeapAlign is a post-training method that improves flow matching model alignment with human preferences by reducing computational costs through two-step trajectory shortcuts while enabling stable gradient propagation to early generation steps. The method outperforms state-of-the-art approaches when fine-tuning Flux models across various image quality and text-alignment metrics.