The authors apply GFlowNet-based reinforcement learning to train LLMs that generate English and Turkish adversarial prompts, reporting improved red-teaming success rates over a prior English-only method.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generating Attacks for LLMs with GFlowNets
The authors apply GFlowNet-based reinforcement learning to train LLMs that generate English and Turkish adversarial prompts, reporting improved red-teaming success rates over a prior English-only method.