Vipera: Blending Visual and LLM-Driven Guidance for Systematic Auditing of Text-to-Image Generative AI

Despite their increasing capabilities, text-to-image generative AI systems are known to produce biased, offensive, and otherwise problematic outputs. While recent advancements have supported testing and auditing of generative AI, existing auditing methods still face challenges in supporting effectively explore the vast space of AI-generated outputs in a structured way. To address this gap, we conducted formative studies with five AI auditors and synthesized five design goals for supporting systematic AI audits. We developed Vipera, an interactive system that blends visual clustering of AI-generated images with LLM-driven prompt suggestions to guide auditors through a structured exploration of model behavior. Vipera helps auditors efficiently identify failure modes and bias patterns across the output space of text-to-image systems.