STAR: SocioTechnical Approach to Red Teaming Language Models
This research introduces STAR, a sociotechnical framework that improves on current best practices for red teaming safety of large language models. STAR makes two key contributions: it enhances steerability by generating parameterised instructions for human red teamers, leading to improved coverage of the risk surface. Parameterised instructions also provide more detailed insights into model failures at no increased cost. Second, STAR improves signal quality by matching demographics to assess harms for specific groups, resulting in more sensitive annotations. STAR further employs a novel step of arbitration to leverage diverse viewpoints and improve label reliability, treating disagreement not as noise but as a valuable contribution to signal quality.
Code (0)
등록된 구현이 없습니다.
Tasks
Red TeamingSimilar Papers 제목 키워드 기반
AI red-teaming is a sociotechnical challenge: on values, labor, and harms
As generative AI technologies find more and more real-world applications, the importance of testing their performance and safety seems paramount. "Red-teaming" has quickly become the primary approach to test AI models--p…
Red TeamingRed Teaming AI Red Teaming
Red teaming has evolved from its origins in military applications to become a widely adopted methodology in cybersecurity and AI. In this paper, we take a critical look at the practice of AI red teaming. We argue that de…
Red TeamingSTAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming
While Large Language Models (LLMs) are widely used, they remain susceptible to jailbreak prompts that can elicit harmful or inappropriate responses. This paper introduces STAR-Teaming, a novel black-box framework for aut…
Red TeamingShaping Influence and Influencing Shaping: A Computational Red Teaming Trust-based Swarm Intelligence Model
Sociotechnical systems are complex systems, where nonlinear interaction among different players can obscure causal relationships. The absence of mechanisms to help us understand how to create a change in the system makes…
Red TeamingAsk What Your Country Can Do For You: Towards a Public Red Teaming Model
AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers f…
Red Teaming