Vipera: Towards systematic auditing of generative text-to-image models at scale

Abstract

Generative text-to-image (T2I) models are known for their risks related such as bias, offense, and misinformation. Current AI auditing methods face challenges in scalability and thoroughness, and it is even more challenging to enable auditors to explore the auditing space in a structural and effective way. Vipera employs multiple visual cues including a scene graph to facilitate image collection sensemaking and inspire auditors to explore and hierarchically organize the auditing criteria. Additionally, it leverages LLM-powered suggestions to facilitate exploration of unexplored auditing directions. An observational user study demonstrates Vipera's effectiveness in helping auditors organize their analyses while engaging with diverse criteria.

Accepted to CHI Late-Breaking Work (LBW) 2025

References in corpus (9)

• Everyday algorithm auditing: Understanding the power of everyday users in surfacing harmful algorithmic behaviors
• Sensecape: Enabling Multilevel Exploration and Sensemaking with Large Language Models
• Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation
• ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing
• Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
• EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria
• Supporting Human-AI Collaboration in Auditing LLMs with LLMs
• Discovering and Validating AI Errors With Crowdsourced Failure Reports
• Farsight: Fostering Responsible AI Awareness During AI Application Prototyping