Full List of Papers

Drawing from Human-Computer Interaction (HCI), Machine Learning (ML), Artificial Intelligence (AI), Organizational Science, Design, Psychology, Crowdsourcing, and Social Computing, my work aims at supporting on-the-ground responsible AI (RAI) practice. I achieve this through an iterative process of empirical understanding and system development, facilitating the meaningful communication and collabroation between AI practitioners and diverse end-users.

I mostly publish at HCI and responsible AI (RAI) venues such as CHI, CSCW, FAccT, AIES, and HCOMP.

2025

WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AI.
Wesley H. Deng, Claire Wang, Howard Ziyu Han, Jason I. Hong*, Kenneth Holstein*, Motahhare Eslami*
arXiv ● PRE-PRINT

* Invited talks at Apple Human-Centered Machine Learning team; Big Design Seminar at Zhejiang University.
Featured as educational materials for more than 600 students across 10 classes at CMU.

Supporting Industry Computing Researchers in Assessing, Articulating, and Addressing the Potential Negative Societal Impact of Their Work
Wesley H. Deng, Solon Barocas*, Jennifer Wortman Vaughan*
CSCW 2025 ● PAPER ● TEMPLATE ● PROJECT PAGE (coming soon)

Human-centered Evaluation and Auditing of Language Models
Yu Lu Liu, Wesley H. Deng, Michelle S. Lam, Motahhare Eslami, Juho Kim, Q. Vera Liao, Wei Xu, Jekaterina Novikova, Ziang Xiao.
CHI 2025 Workshop Proposal ● WEBSITE

2024

Red-Teaming for Generative AI: Silver Bullet or Security Theater?
Michael Feffer, Anusha Sinha, Wesley H. Deng, Zachary C. Lipton, Hoda Heidari
AIES 2024 ● Best Paper Award ● PAPER

Investigating What Factors Influence Users’ Detection of Harmful Algorithmic Bias and Discrimination.
Sara Kingsley*, Jiayin Zhi*, Wesley H. Deng, Jaimie Lee, Sizhe Zhang, Motahhare Eslami*, Kenneth Holstein*, Joson I. Hong*, Tianshi Li*, Hong Shen*
HCOMP 2024 ● Best Paper Award ● PAPER

Responsible Crowdsourcing for Responsible Generative AI: Engaging Crowds in AI Auditing and Evaluation
Wesley H. Deng, Mireia Yurrita, Mark Díaz, Jina Suh, Nick Judd, Lara Groves, Hong Shen*, Motahhare Eslami*, Kenneth Holstein*.
HCOMP 2024 Workshop Proposal ● PROPOSAL ● WEBSITE

MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI.
Matheus Kunzler Maldaner, Wesley H. Deng, Jason I. Hong*, Ken Holstein*, Motahhare Eslami*.
HCOMP 2024 DEMO ● PAPER ● DEMO

Designing a Crowdsourcing Pipeline to Verify Reports from User AI Audits
Wang Claire, Wesley H. Deng, Jason I. Hong*, Ken Holstein*, Motahhare Eslami*.
HCOMP 2024 WiP ● PAPER

Human-centered Evaluation and Auditing of Language Models
Ziang Xiao, Wesley H. Deng, Michelle S. Lam, Motahhare Eslami, Juho Kim, Mina Lee, Q. Vera Liao.
CHI 2024 Workshop Proposal ● PROPOSAL ● WEBSITE

Collaboratively Designing and Evaluating Responsible AI Interventions
Wesley H. Deng, Glen Berman, Harmanpreet Kaur, Reva Schwartz, Memunat A Ibrahim, Motahhare Eslami, Kenneth Holstein, Michael Madaio.
CSCW 2024 Workshop Proposal ● PROPOSAL ● WEBSITE

Troubling Taxonomies in GenAI Evaluation.
Glen Berman, Ned Cooper, Wesley H. Deng, Ben Hutchinson
NeurIPS 2024 Workshop on Evaluating Evaluations ● PAPER

Carefully Unmaking the “Marginalized User”: A Diffractive Analysis of a Gay Online Community.
Jordan Taylor, Wesley H. Deng, Kenneth Holstein, Sarah Fox, Haiyi Zhu
Transactions on Computer-Human Interaction ● PAPER

2023

Understanding Practices, Challenges, and Opportunities for User-Engaged Algorithm Auditing in Industry Practice
Wesley H. Deng, Boyuan Guo, Alicia DeVrio, Hong Shen, Motahhare Eslami*, Kenneth Holstein*
CHI 2023 ● PAPER ● VIDEO

* Invited talks at Faculty of EEMCS and Industrial Design Engineering at TU Delft, Algorithmic Fairness and Opacity (AFOG) Group at UC Berkeley, Tecent Shanghai, Google Shanghai, Salesforce, and Capital One.

Investigating Practices and Opportunities for Cross-functional Collaboration around AI Fairness in Industry Practice
Wesley H. Deng, Nur Yildrim, Monica Chang, Motahhare Eslami, Kenneth Holstein, Michael Madaio
FAccT 2023 ● PAPER ● VIDEO

Supporting User Engagement in Testing, Auditing, and Contesting AI
Wesley H. Deng, Michelle S Lam, Ángel Alexander Cabrera, Danaë Metaxa, Motahhare Eslami*, Kenneth Holstein*.
CSCW 2023 Workshop Proposal ● PROPOSAL ● WEBSITE

Towards" Anytime, Anywhere" Community Learning and Engagement around the Design of Public Sector AI
Wesley H. Deng, Motahhare Eslami*, Kenneth Holstein*.
CHI 2023 Workshop on AI Literacy ● PAPER

2022

Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
Wesley H. Deng, Manish Nagireddy, Michelle Seng Ah Lee, Jatinder Singh, Zhiwei Steven Wu, Kenneth Holstein, Haiyi Zhu
FAccT 2022 ● PAPER ● VIDEO

* Invited talks at FairLearn developer teams at Microsoft Research, AIF360 developer monthly meeting at IBM, People+AI Research team at Google, and AI Governance group at PwC.

The model card authoring toolkit: Toward community-centered, deliberation-driven AI design
Hong Shen, Leijie Wang, Wesley H. Deng, Ciell Brusse, Ronald Velgersdijk, Haiyi Zhu
FAccT 2022 ● PAPER ● VIDEO

Opportunities for human-centered evaluation of machine translation systems
Daniel Liebling, Katherine Heller, Samantha Robertson, Wesley H. Deng
NAACL 2022 ● PAPER

Beyond General Purpose Machine Translation: The Need for Context-specific Empirical Research to Design for Appropriate User Trust
Wesley H. Deng, Nikita Mehandru, Samantha Robertson, Niloufar Salehi.
CHI 2022 Workshop on Trust and Reliance in AI-Human Teaming ● PAPER

2021

Value cards: An educational toolkit for teaching social impacts of machine learning through deliberation
Hong Shen, Wesley H. Deng, Aditi Chattopadhyay, Zhiwei Steven Wu, Xu Wang, Haiyi Zhu
FAccT 2021 ● PAPER ● VIDEO

Robust Laughter Detection in Noisy Environments
Jon Gillick, Wesley H. Deng, Kimiko Ryokai, David Bamman
Interspeech 2021 ● PAPER ● GITHUB

Three Directions for the Design of Human-Centered Machine Translation
Samantha Robertson, Wesley H. Deng, Timnit Gebru, Margaret Mitchell, Daniel J Liebling, Michal Lahav, Katherine Heller, Mark Díaz, Samy Bengio, Niloufar Salehi
ACL HCI + NLP Workshop ● PAPER ●

2020

Personal laughter archives: reflection through visualization and interaction
Kimiko Ryokai, Julia Park, Wesley H. Deng.
UbiComp Work in Progress ● PAPER