Clarify: Improving Model Robustness With Natural Language Corrections

no code implementations • 6 Feb 2024 • Yoonho Lee, Michelle S. Lam, Helena Vasconcelos, Michael S. Bernstein, Chelsea Finn

Additionally, we use Clarify to find and rectify 31 novel hard subpopulations in the ImageNet dataset, improving minority-split accuracy from 21. 1% to 28. 7%.

Misconceptions

Generation Probabilities Are Not Enough: Exploring the Effectiveness of Uncertainty Highlighting in AI-Powered Code Completions

no code implementations • 14 Feb 2023 • Helena Vasconcelos, Gagan Bansal, Adam Fourney, Q. Vera Liao, Jennifer Wortman Vaughan

Through a mixed-methods study with 30 programmers, we compare three conditions: providing the AI system's code completion alone, highlighting tokens with the lowest likelihood of being generated by the underlying generative model, and highlighting tokens with the highest predicted likelihood of being edited by a programmer.

Code Completion

Explanations Can Reduce Overreliance on AI Systems During Decision-Making

no code implementations • 13 Dec 2022 • Helena Vasconcelos, Matthew Jörke, Madeleine Grunde-McLaughlin, Tobias Gerstenberg, Michael Bernstein, Ranjay Krishna

Prior work has identified a resilient phenomenon that threatens the performance of human-AI decision-making teams: overreliance, when people agree with an AI, even when it is incorrect.

Decision Making