5 papers
PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI
Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim +5
Recent developments in AI safety research have called for red-teaming methods that effectively surface potential risks posed by generative AI models, with growing emphasis on how r…
Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
Sunnie S. Y. Kim, Margit Bowler, Leon A Gatys
Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building with users, to refusing reque…
Understanding Annotator Safety Policy with Interpretability
Alex Oesterling, Donghao Ren, Yannick Assogba +4
Safety policies define what constitutes safe and unsafe AI outputs, guiding data annotation and model development. However, annotation disagreement is pervasive and can stem from m…
VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety
Shruti Palaskar, Leon Gatys, Mona Abdelrahman +9
Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful i…
SafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation
Alec Helbling, Shruti Palaskar, Kundan Krishna +3
What exactly makes a particular image unsafe? Systematically differentiating between benign and problematic images is a challenging problem, as subtle changes to an image, such as…