Hello World!
I'm Sherry Tongshuang Wu
(吴彤霜)!
Assistant Professor
School of CS, Carnegie Mellon University (CMU SCS)
Human Computer Interaction Institute (HCII, primary)
Language Technololgy Institute (LTI, affiliated)

I am trained (by my amazing PhD advisors Jeffrey Heer and Dan Weld at the University of Washington) to be an HCI+NLP researcher. I study how humans (AI experts, lay users, domain experts) interact with (debug, audit, collaborate) AI systems.

Most recently, I try to answer:

How can people identify, improve, and cope with imperfect AI models, while still benefiting from their use?

Click & jump to some recent papers that represent my research interests and style (or read my Research Statement):
If you are interested in exploring relevant topics with me at CMU, I will be looking for undergraduate, graduate, and postdoctoral students! Feel free to email me if you'd like to chat :)

Research Highlights

Data-centric AI usage
Tailor: Generating and Perturbing Text with Semantic Controls
Tongshuang Wu*, Alexis Ross*, Hao Peng, Matthew E. Peters, Matt Gardner
ACL 2022: the 60th Annual Meeting of the Association for Computational Linguistics
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models
Tongshuang Wu, Marco Tulio Ribeiro, Jeffrey Heer, Daniel S. Weld
ACL 2021: the 59th Annual Meeting of the Association for Computational Linguistics
Tempura: Query Analysis with Structural Templates
Tongshuang Wu, Kanit (Ham) Wongsuphasawat, Donghao Ren, Kayur Patel, Chris DuBois
CHI 2020: the 2020 Conference on Human Factors in Computing Systems
Practical AI Evaluation
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Tongshuang Wu*, Gagan Bansal*, Joyce Zhou+, Raymond Fok+, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, Daniel S. Weld
CHI 2021: the 2021 Conference on Human Factors in Computing Systems
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList Best Paper
Marco Tulio Ribeiro, Tongshuang Wu, Carlos Guestrin, Sameer Singh
ACL 2020: the 58th Annual Meeting of the Association for Computational Linguistics
Errudite: Scalable, Reproducible, and Testable Error Analysis
Tongshuang Wu, Marco Tulio Ribeiro, Jeffrey Heer, Daniel S. Weld
ACL 2019: the 57th Annual Meeting of the Association for Computational Linguistics
Interpretable & Controllable Human-AI Interaction
AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts
Tongshuang Wu, Michael Terry, Carrie J. Cai
CHI 2022: the 2022 Conference on Human Factors in Computing Systems
Are Shortest Rationales the Best Explanations for Human Understanding?
Hua Shen, Tongshuang Wu, Wenbo Guo, Daniel Ritchie, Ting-Hao 'Kenneth' Huang
ACL 2022: the 60th Annual Meeting of the Association for Computational Linguistics