conftrace_

misaligned behavior

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

automated red teaming (1) risk taxonomy (1) large language model (1) adversarial probing (1) test case generation (1) red teaming (1) multi-turn interaction (1) model alignment (1) reinforcement learning (1)

Papers

Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction EMNLP 2024