← All publications

Human-AI Collaboration

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

Yanwei Huang, Wesley Hanwen Deng, Sijia Xiao, Motahhare Eslami, Jason I. Hong, Arpit Narechania, Adam Perer

ACM CHI · 2026

PDF DOI Demo Code

Abstract

We developed Vipera, an interactive auditing interface that employs multiple visual cues, including a scene graph, to facilitate image sensemaking and inspire auditors to explore and hierarchically organize auditing criteria, with LLM-powered suggestions for unexplored directions.

Citation

@inproceedings{huang2026vipera,
  author = {Huang, Yanwei and Deng, Wesley Hanwen and Xiao, Sijia and Eslami, Motahhare and Hong, Jason I. and Narechania, Arpit and Perer, Adam},
  title = {{Vipera: Blending Visual and LLM-Driven Guidance for Systematic Auditing of Text-to-Image Generative AI}},
  booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},
  year = {2026},
  publisher = {ACM},
  pages = {1--18},
  doi = {10.1145/3772318.3791942}
}