Papers

Towards Conceptualization of “Fair Explanation”: Impact of Asian Hate Speech Explanations on Content Moderators Joint work with Tin Nguyen, Aayushi Roy, Hal Daumé III, and Marine Carpuat.

Working Projects

Personalized Assortment Optimization for a Subscription Business Model of Experience Goods Joint work with Gah-Yi Ban, Wedad J. Elmaghraby, and L. Beril Toktay.

Crafting Freelance Success: Unveiling the Impact of Availability on Match Quality through Conversational Analytics Joint work with Ashish S. Kabra and Kunpeng Zhang.

From Complexity to Clarity: Trustworthy NLP to Alleviate Disparity in Credit Card Debt Joint work with Jane Jiang and Wedad J. Elmaghraby.

A Colletion of Computer Science Projects

Technical AI Fairness Criteria Might Constitutionally Apply to U.S. Recidivism Risk Assessment Tools, but How and for Whom? Joint work with Tin Nguyen, Kem Nguyen-Le, Donald Braman, Jonathan Lazar, Hal Daumé III, and Zubin Jelveh

Effort-aware Fairness: Measures and Mitigations in AI-assisted Decision Making Joint work with Tin Nguyen, Zora Che, Kem Nguyen-Le, Donald Braman, Hal Daumé III, Furong Huang, and Zubin Jelveh

Bipartite Networked Multi-agent Reinforcement Learning for Decentralized Matching Markets Joint work with Yan Xu.