About
I am a fourth year Ph.D. student at the University of Maryland, College Park in the Department of Computer Science advised by Prof. Hal Daumé III. My current research focuses on fairness in NLP, human-AI interaction, and their intersection. More broadly, I am interested in fairness, trust/reliance, and interpretability in AI systems. Some questions that I ask in my research are:
- When people interact with a model exhibiting certain biases (or even a "debiased" model), what are the tangible effects/harms on the person?
- When people work together with a model to make decisions, how can we encourage outcomes that are more fair to the people affected by these decisions?
Previously, I did a combined BS/MS in Computer Science (with a secondary major in Japanese Studies and a concentration in AI) at Case Western Reserve University, advised by Prof. Soumya Ray.
Selected Publications and Preprints
Anti-stereotypical Predictive Text Suggestions Do Not Reliably Yield Anti-stereotypical Writing
Connor Baumler and Hal Daumé III
2024
[Paper]
[Repo]
[arXiv]
The Impact of Explanations on Fairness in Human-AI Decision Making: Protected vs Proxy Features
Connor Baumler*, Navita Goyal*, Tin Nguyen, and Hal Daumé III
IUI 2024
A preliminary version of this paper appeared at the CHI 2023 Workshop on Trust and Reliance in AI-Assisted Tasks (TRAIT).
[Paper]
[Repo]
[ACM]
Which Examples Should be Multiply Annotated? Active Learning When Annotators May Disagree
Connor Baumler*, Anna Sotnikova*, and Hal Daumé III
Finding of ACL 2023
[Paper]
[Repo]
[ACL Anthology]
Recognition of They/Them as Singular Personal Pronouns in Coreference Resolution
Connor Baumler and Rachel Rudinger
NAACL 2022
[Paper]
[Repo]
[ACL Anthology]