156 citations · 467 across the 38 of their papers we have counts for
15 papers · 1 filter
Seeing Twice: How Side-by-Side T2I Comparison Changes Auditing Strategies
Matheus Kunzler Maldaner, Wesley Hanwen Deng, Jason I. Hong +2
While generative AI systems have gained popularity in diverse applications, their potential to produce harmful outputs limits their trustworthiness and utility. A small but growing…
Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations
Eunkyu Park, Wesley Hanwen Deng, Vasudha Varadarajan +4
Explanations are often promoted as tools for transparency, but they can also foster confirmation bias; users may assume reasoning is correct whenever outputs appear acceptable. We…
PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
Wesley Hanwen Deng, Sunnie S. Y. Kim, Akshita Jha +4
Recent developments in AI governance and safety research have called for red-teaming methods that can effectively surface potential risks posed by AI models. Many of these calls ha…
Vipera: Blending Visual and LLM-Driven Guidance for Systematic Auditing of Text-to-Image Generative AI
Yanwei Huang, Wesley Hanwen Deng, Sijia Xiao +4
Despite their increasing capabilities, text-to-image generative AI systems are known to produce biased, offensive, and otherwise problematic outputs. While recent advancements have…
"I Don't Think RAI Applies to My Model'' -- Engaging Non-champions with Sticky Stories for Responsible AI Work
Nadia Nahar, Chenyang Yang, Yanxin Chen +4
Responsible AI (RAI) tools -- checklists, templates, and governance processes -- often engage RAI champions, individuals intrinsically motivated to advocate ethical practices, but…
Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations
Eunkyu Park, Wesley Hanwen Deng, Gunhee Kim +2
Chain-of-Thought (CoT) prompting helps models think step by step. But naive CoT breaks down in visually grounded social tasks, where models must perceive, understand, and judge all…
A Human-Centered Approach to Identifying Promises, Risks, & Challenges of Text-to-Image Generative AI in Radiology
Katelyn Morrison, Arpit Mathur, Aidan Bradshaw +7
As text-to-image generative models rapidly improve, AI researchers are making significant advances in developing domain-specific models capable of generating complex medical imager…
What Comes After Harm? Mapping Reparative Actions in AI through Justice Frameworks
Sijia Xiao, Haodi Zou, Alice Qian Zhang +4
As Artificial Intelligence (AI) systems are integrated into more aspects of society, they offer new capabilities but also cause a range of harms that are drawing increasing scrutin…
Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences
Mingqian Zheng, Wenjia Hu, Patrick Zhao +5
Current LLMs are trained to refuse potentially harmful input queries regardless of whether users actually had harmful intents, causing a tradeoff between safety and user experience…
MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI
Matheus Kunzler Maldaner, Wesley Hanwen Deng, Jason Hong +2
While generative AI systems have gained popularity in diverse applications, their potential to produce harmful outputs limits their trustworthiness and usability in different appli…
Vipera: Towards systematic auditing of generative text-to-image models at scale
Yanwei Huang, Wesley Hanwen Deng, Sijia Xiao +3
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 th…
Emerging Practices in Participatory AI Design in Public Sector Innovation
Devansh Saxena, Zoe Kahn, Erina Seh-Young Moon +9
Local and federal agencies are rapidly adopting AI systems to augment or automate critical decisions, efficiently use resources, and improve public service delivery. AI systems are…
Investigating Youth AI Auditing
Jaemarie Solyst, Cindy Peng, Wesley Hanwen Deng +5
Youth are active users and stakeholders of artificial intelligence (AI), yet they are often not included in responsible AI (RAI) practices. Emerging efforts in RAI largely focus on…
A Systematic Literature Review on Equity and Technology in HCI and Fairness: Navigating the Complexities and Nuances of Equity Research
Seyun Kim, Yuanchen Bai, Haiyi Zhu +1
Equity is crucial to the ethical implications in technology development. However, implementing equity in practice comes with complexities and nuances. In response, the research com…
WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AI
Wesley Hanwen Deng, Wang Claire, Howard Ziyu Han +3
There has been growing interest from both practitioners and researchers in engaging end users in AI auditing, to draw upon users' unique knowledge and lived experiences. However, w…