83 citations · 332 across the 12 of their papers we have counts for
12 papers
An In-depth Look at Gemini's Language Abilities
Syeda Nahida Akter, Zichun Yu, Aashiq Muhamed +6
The recently released Google Gemini class of models are the first to comprehensively report results that rival the OpenAI GPT series across a wide variety of tasks. In this paper,…
Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Nari Johnson, Ángel Alexander Cabrera, Gregory Plumb +1
Machine learning (ML) models that achieve high average accuracy can still underperform on semantically coherent subsets ("slices") of data. This behavior can have significant socie…
Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning
Ángel Alexander Cabrera, Erica Fu, Donald Bertucci +4
Machine learning models with high accuracy on test data can still produce systematic failures, such as harmful biases and safety issues, when deployed in the real world. To detect…
Improving Human-AI Collaboration With Descriptions of AI Behavior
Ángel Alexander Cabrera, Adam Perer, Jason I. Hong
People work with AI systems to improve their decision making, but often under- or over-rely on AI predictions and perform worse than they would have unassisted. To help people appr…
Towards a More Rigorous Science of Blindspot Discovery in Image Classification Models
Gregory Plumb, Nari Johnson, Ángel Alexander Cabrera +1
A growing body of work studies Blindspot Discovery Methods ("BDM"s): methods that use an image embedding to find semantically meaningful (i.e., united by a human-understandable con…
"Public(s)-in-the-Loop": Facilitating Deliberation of Algorithmic Decisions in Contentious Public Policy Domains
Hong Shen, Ángel Alexander Cabrera, Adam Perer +1
This position paper offers a framework to think about how to better involve human influence in algorithmic decision-making of contentious public policy issues. Drawing from insight…
Symphony: Composing Interactive Interfaces for Machine Learning
Alex Bäuerle, Ángel Alexander Cabrera, Fred Hohman +5
Interfaces for machine learning (ML), information and visualizations about models or data, can help practitioners build robust and responsible ML systems. Despite their benefits, r…
Discovering and Validating AI Errors With Crowdsourced Failure Reports
Ángel Alexander Cabrera, Abraham J. Druck, Jason I. Hong +1
AI systems can fail to learn important behaviors, leading to real-world issues like safety concerns and biases. Discovering these systematic failures often requires significant dev…
Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)
Gregory Plumb, Maruan Al-Shedivat, Eric Xing +1
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post…
FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning
Ángel Alexander Cabrera, Will Epperson, Fred Hohman +3
The growing capability and accessibility of machine learning has led to its application to many real-world domains and data about people. Despite the benefits algorithmic systems m…
Regularizing Black-box Models for Improved Interpretability
Gregory Plumb, Maruan Al-Shedivat, Angel Alexander Cabrera +3
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post…
Interactive Classification for Deep Learning Interpretation
Ángel Alexander Cabrera, Fred Hohman, Jason Lin +1
We present an interactive system enabling users to manipulate images to explore the robustness and sensitivity of deep learning image classifiers. Using modern web technologies to…