一作ACL 2026Poster· Natural Language Processing
Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLM s in the Financial Domain
Gang Cheng · Haibo Jin · Wenbin Zhang · Haohan Wang · Jun Zhuang
摘要
Large Language Models (LLMs) are increasingly deployed in finance, where unsafe behavior can lead to serious regulatory risks. However, most red-teaming research focuses on overtly harmful content and overlooks attacks that appear legitimate on the surface yet induce regulatory-violating response...