Conference Human-Agent Interaction & 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

DOI PDF Demo Code

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

Abstract

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 effective exploration of 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. Based on these insights, 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 the auditing criteria. Additionally, Vipera leverages LLM-powered suggestions to enable exploration of unexplored auditing directions. Through a controlled experiment with 24 participants experienced in AI auditing, we demonstrate Vipera’s effectiveness in helping auditors navigate large AI output spaces and organize their analyses while engaging with diverse criteria.

Citation

@inproceedings{huang2026vipera,
  author = {Huang, Yanwei and Hanwen Deng, Wesley 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}},
  year = {2026},
  isbn = {9798400722783},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3772318.3791942},
  doi = {10.1145/3772318.3791942},
  booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},
  articleno = {698},
  numpages = {18},
  series = {CHI '26}
}