collaborators

5 papers

cs.HC2026

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…

cs.HC2026

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…

cs.AI2026

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…

cs.CV2025

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…

cs.CV2025

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…