Jenn Wortman Vaughan


I am a Senior Principal Researcher at Microsoft Research, New York City, a collaborative and interdisciplinary basic research lab.

I work on responsible AI—specifically transparency, interpretability, and fairness of AI systems—as part of Microsoft's FATE group and Co-Chair of Microsoft's Aether working group on transparency. I am interested in the interaction between people and AI. My passion is for AI that augments, rather than replaces, human abilities. My research background is in machine learning and algorithmic economics, and a big fraction of my work has been theoretical—I like a nice clean model that captures the essence of a problem and provable guarantees—but, thanks to the amazing interdisciplinary environment where I work, I now incorporate experiments and even qualitative methods into my research in order to better understand human behavior in sociotechnical systems.

For a more complete picture of my research, take a look at some of my publications.

I am very active in the research community. I recently served as Program Co-Chair of NeurIPS 2021. I have also served as the (Program and General) Co-Chair of HCOMP 2019, the Workshops Chair of NeurIPS 2019, the Tutorial Co-Chair of both NeurIPS 2017 and 2018, the Workshops Co-Chair of both EC 2017 and 2018, the Press Co-Chair of ICML 2019, and the Secretary-Treasurer of SigEcom from 2015-2019. I am currently a Steering Committee Member of ACM FAccT. I was a long-term Senior Advisor to WiML, which I co-founded back in 2006.

At MSR I have had the opportunity to work with an amazing set of interns. Typically our interns are Ph.D. students with strong publication records in areas relevant to our lab, but MSR also runs a small internship program for undergrads. Internship opportunities are typically advertised in the fall.

I reluctantly tweet as @jennwvaughan.

Quick Links and Resources

Transparency and intelligibility: book chapter, webinar, podcast episode, trustworthly ml seminar, NeurIPS workshop talk

Fairness: FTC keynote, webinar, tutorial overview and video from FAT*

Crowdsourcing: tutorial overview and video from NeurIPS, JMLR survey article

My standard bio (for talk announcements, etc.) is here.

What's New?

There are several opportunities to collaborate with the FATE group with deadlines in November/December 2023! Consider applying for our 2024 internships, postdoc, or new AI & Society fellowships.

Vera Liao and I posted a new paper laying out our vision of a human-centered research roadmap for “AI Transparency in the Age of LLMs” which we hope will spark more discussion and research. Constructive feedback is very welcome!

I hosted a NIST panel on why meaningful human oversight is so elusive and throwing a human in the loop is not enough. Video available here (panel 13).

I have been serving as Program Co-Chair of NeurIPS 2021. To learn more about what we've done this year, see our blog posts on the NeurIPS paper checklist, the move to OpenReview, this year's keynote speakers and plenary panels, the ethics review process, the consistency experiment, and the author perception experiment.

I recently participated in a White House OSTP panel on AI and Democratic Values.

I've been giving a bunch of virtual talks on human-centered approaches to intelligible machine learning. You can view videos from the Trustworthy ML Initiative seminar (longer version) or the NeurIPS HAMLETS workshop (shorter version).

Listen to me talk about AI transparency, my research journey from machine learning theory to human-centered responsible AI, and pessimism as a super power on the Radical AI podcast.

More activities...


I came to MSR-NYC from UCLA where I was an Assistant Professor in the Computer Science Department. Prior to that I spent a year as a Computing Innovation Fellow at Harvard University where I was a member of the EconCS group and the Theory group, and an affiliate of the Center for Research on Computation and Society.

I received my Ph.D. in Computer and Information Science from the University of Pennsylvania in 2009. I was extremely lucky to be advised by Michael Kearns. My doctoral dissertation, Learning from Collective Preferences, Behavior, and Beliefs, introduced a series of new learning models and algorithms designed to address the problems commonly faced when aggregating local information across large population, and was awarded Penn's Rubinoff award for innovative applications of computer technology. During my time at Penn, I spent two fun summers interning in New York, first with the Machine Learning and Microeconomics groups at Yahoo! Research and then in the research group at Google.

Before coming to Penn, I completed a Masters in Computer Science at Stanford where I got my first taste of research working with the Multiagent Group. Further back in the day, I was a carefree undergrad at BU.

You might remember me as Jenn Wortman. When I got married, I took Vaughan (pronounced "von") as my "official" last name and moved Wortman to my middle name. This never fails to confuse people. I use both names together professionally and prefer that you do too.

Get In Touch

The best way to reach me is by email. I am jenn at