STAR: SocioTechnical Approach to Red Teaming Language Models

Autor:	Weidinger, Laura, Mellor, John, Pegueroles, Bernat Guillen, Marchal, Nahema, Kumar, Ravin, Lum, Kristian, Akbulut, Canfer, Diaz, Mark, Bergman, Stevie, Rodriguez, Mikel, Rieser, Verena, Isaac, William
Rok vydání:	2024
Předmět:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Computers and Society Computer Science - Human-Computer Interaction
Druh dokumentu:	Working Paper
Popis:	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. Comment: 8 pages, 5 figures, 5 pages appendix. * denotes equal contribution
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.11757 Zobrazit plný text záznamu View this record from Arxiv