一作ACL 2026Findings· Findings of ACL
Reverse Constitutional AI : A Framework for Controllable Toxic Data Generation via Probability-Clamped RLAIF
Yuan Fang · Yiming Luo · Aimin Zhou · Fei Tan
摘要
Ensuring the safety of large language models (LLMs) requires robust red teaming, yet the systematic synthesis of high-quality toxic data remains under-explored. We propose Reverse Constitutional AI (R-CAI), a framework for automated and controllable adversarial data generation that moves beyond i...