paper-with-me

홈 › Papers

Automatic LLM Red Teaming

2025-08-06 · Roman Belaire, Arunesh Sinha, Pradeep Varakantham arxiv

Red teaming is critical for identifying vulnerabilities and building trust in current LLMs. However, current automated methods for Large Language Models (LLMs) rely on brittle prompt templates or single-turn attacks, failing to capture the complex, interactive nature of real-world adversarial dialogues. We propose a novel paradigm: training an AI to strategically `break' another AI. By formalizing red teaming as a Markov Decision Process (MDP) and employing a hierarchical Reinforcement Learning (RL) framework, we effectively address the inherent sparse reward and long-horizon challenges. Our generative agent learns coherent, multi-turn attack strategies through a fine-grained, token-level harm reward, enabling it to uncover subtle vulnerabilities missed by existing baselines. This approach sets a new state-of-the-art, fundamentally reframing LLM red teaming as a dynamic, trajectory-based process (rather than a one-step test) essential for robust AI deployment.

📄 PDF Abstract BibTeX arXiv:2508.04451

Code (0)

등록된 구현이 없습니다.

Tasks

Hierarchical Reinforcement LearningRed Teaming

Similar Papers 제목 키워드 기반

MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

2023-11-13 · Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa 외

Red-teaming is a common practice for mitigating unsafe behaviors in Large Language Models (LLMs), which involves thoroughly assessing LLMs to identify potential flaws and addressing them with responsible and accurate res…

Instruction FollowingRed TeamingResponse GenerationSafety Alignment

Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming

2025-02-22 · Rui Li, Peiyi Wang, Jingyuan Ma, Di Zhang 외

Large Language Models (LLMs) have gained increasing attention for their remarkable capacity, alongside concerns about safety arising from their potential to produce harmful content. Red teaming aims to find prompts that …

DiversityIn-Context LearningRed Teaming

PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming

2025-09-03 · Wesley Hanwen Deng, Sunnie S. Y. Kim, Akshita Jha, Ken Holstein 외 arxiv

Recent developments in AI governance and safety research have called for red-teaming methods that can effectively surface potential risks posed by AI models. Many of these calls have emphasized how the identities and bac…

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools

2025-09-25 · Ping He, Changjiang Li, Binbin Zhao, Tianyu Du 외 arxiv

The remarkable capability of large language models (LLMs) has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context…

Red Teaming

Gradient-Based Language Model Red Teaming

2024-01-30 · Nevan Wichers, Carson Denison, Ahmad Beirami

Red teaming is a common strategy for identifying weaknesses in generative language models (LMs), where adversarial prompts are produced that trigger an LM to generate unsafe responses. Red teaming is instrumental for bot…

Language ModelingLanguage ModellingmodelPrompt Learning+1