Molly Q Feldman
Photo of Molly
she/her

Announcements

  • MultiPL-T accepted to OOPSLA
  • StudentEval full paper appeared in ACL Findings 2024
  • Our StudentEval submission won best presentation at LLM4Code 2024 - Congrats Sydney!

I am an Assistant Professor of Computer Science at Oberlin College.

Prior to Oberlin, I was a Visiting Assistant Professor at Williams College and received my Ph.D. in Computer Science from Cornell University in 2020. I started my liberal arts experience at Swarthmore College, where I completed a B.A. in Mathematics & Computer Science.

A full CV is available here.

Teaching

I teach courses across the Oberlin CS curriculum from CS1 to Programming Languages to HCI. I am on junior faculty research leave for 24-25, so I am not currently teaching. However, some recent courses include:

CSCI 275: Programming Abstractions
This course covers programming languages fundamentals and functional programming in Racket.
CSCI 317: People-Powered Procedures
This course overviews the many ways people contribute to the programming pipeline, including data labeling, human aspects of software engineering, and AI interaction.

Research

I'm interested in bridging the gap between powerful computational methods and the human-centered world. Specifically, my work considers how methods that are newly practical can be adapted to solve complex human problems in meaningful ways. This work has been made possible by my collaborators and co-authors.

I am grateful for support from the National Science Foundation to explore these questions.

Selected Publications

Looking for a paper not listed here? Check Google Scholar.
StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Code
Hannah McLean Babe, Sydney Nguyen, Yangtian Zi, Arjun Guha, Molly Q Feldman & Carolyn Jane Anderson
Non-Expert Programmers in the Generative AI Future
Molly Q Feldman & Carolyn Jane Anderson
How Beginning Programmers and Code LLMs Mis(read) Each Other
Sydney Nguyen, Hannah McLean Babe, Yangtian Zi, Arjun Guha, Carolyn Jane Anderson & Molly Q Feldman
MultiPL-E: A Scalable and Polyglot Approach to Benchmarking Neural Code Generation
Federico Cassano, John Gouwar, Daniel Nguyen, Sydney Nguyen, Luna Phipps-Costin, Donald Pinckney, Ming-Ho Yee, Yangtian Zi, Carolyn Jane Anderson, Molly Q Feldman, Arjun Guha, Michael Greenberg & Abhinav Jangda
How we write with crowds
Molly Q Feldman & Brian McInnis
Automatic Diagnosis of Students' Misconceptions in K-8 Mathematics
Molly Q Feldman, Ji Yong Cho, Monica Ong, Sumit Gulwani, Zoran Popović & Erik Andersen