E
Elena L. Glassman
Researcher at Harvard University
Publications - 58
Citations - 1334
Elena L. Glassman is an academic researcher from Harvard University. The author has contributed to research in topics: Computer science & Program synthesis. The author has an hindex of 16, co-authored 46 publications receiving 805 citations. Previous affiliations of Elena L. Glassman include University of California, Berkeley & Massachusetts Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Proxy tasks and subjective measures can be misleading in evaluating explainable AI systems
TL;DR: This work conducted two online experiments and one in-person think-aloud study to evaluate two currently common techniques for evaluating XAI systems: using proxy, artificial tasks such as how well humans predict the AI's decision from the given explanations, and using subjective measures of trust and preference as predictors of actual performance.
Journal ArticleDOI
OverCode: Visualizing Variation in Student Solutions to Programming Problems at Scale
TL;DR: OverCode is presented, a system for visualizing and exploring thousands of programming solutions that allows teachers to more quickly develop a high-level view of students' understanding and misconceptions, and to provide feedback that is relevant to more students' solutions.
Proceedings ArticleDOI
Writing Reusable Code Feedback at Scale with Mixed-Initiative Program Synthesis
Andrew Head,Elena L. Glassman,Gustavo Soares,Ryo Suzuki,Lucas Figueredo,Loris D'Antoni,Björn Hartmann +6 more
TL;DR: A mixed-initiative approach which combines teacher expertise with data-driven program synthesis techniques is introduced which helps teachers better understand student bugs and write reusable feedback that scales to a massive introductory programming classroom.
Proceedings ArticleDOI
Expectation vs. Experience: Evaluating the Usability of Code Generation Tools Powered by Large Language Models
TL;DR: It was found that, while Copilot did not necessarily improve the task completion time or success rate, most participants preferred to use Copilot in daily programming tasks, since Copilot often provided a useful starting point and saved the effort of searching online.
Journal ArticleDOI
A wavelet-like filter based on neuron action potentials for analysis of human scalp electroencephalographs
TL;DR: The development and testing of a wavelet-like filter, named the SNAP, created from a neural activity simulation and used, in place of aWavelet, in a wavelets/filters transform for improving EEG wavelet analysis, intended for brain-computer interfaces.