research
∙
06/05/2023
AHA!: Facilitating AI Impact Assessment by Generating Examples of Harms
While demands for change and accountability for harmful AI consequences ...
share
research
∙
05/28/2023
Targeted Data Generation: Finding and Fixing Model Weaknesses
Even when aggregate accuracy is high, state-of-the-art NLP models often ...
research
∙
05/20/2023
Collaborative Development of NLP models
Despite substantial advancements, Natural Language Processing (NLP) mode...
research
∙
04/19/2023
Supporting Human-AI Collaboration in Auditing LLMs with LLMs
Large language models are becoming increasingly pervasive and ubiquitous...
research
∙
03/22/2023
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Artificial intelligence (AI) researchers have been developing and refini...
research
∙
03/16/2023
ART: Automatic multi-step reasoning and tool-use for large language models
Large language models (LLMs) can perform complex reasoning in few- and z...
research
∙
02/14/2023
ScatterShot: Interactive In-context Example Curation for Text Transformation
The in-context learning capabilities of LLMs like GPT-3 allow annotators...
research
∙
12/08/2022
Editing Models with Task Arithmetic
Changing how pre-trained models behave – e.g., improving their performan...
research
∙
12/06/2022
Adaptive Testing of Computer Vision Models
Vision models often fail systematically on groups of data that share com...
research
∙
11/07/2022
Fixing Model Bugs with Natural Language Patches
Current approaches for fixing systematic problems in NLP models (e.g. re...
research
∙
07/08/2022
Evaluating Systemic Error Detection Methods using Synthetic Images
We introduce SpotCheck, a framework for generating synthetic datasets to...
research
∙
04/30/2022
ExSum: From Local Explanations to Model Understanding
Interpretability methods are developed to understand the working mechani...
research
∙
06/03/2021
Finding and Fixing Spurious Patterns with Explanations
Machine learning models often use spurious patterns such as "relying on ...
research
∙
01/01/2021
Polyjuice: Automated, General-purpose Counterfactual Generation
Counterfactual examples have been shown to be useful for many applicatio...
research
∙
06/26/2020
Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance
Increasingly, organizations are pairing humans with AI systems to improv...
research
∙
05/08/2020
Beyond Accuracy: Behavioral Testing of NLP models with CheckList
Although measuring held-out accuracy has been the primary approach to ev...
research
∙
11/22/2016
Programs as Black-Box Explanations
Recent work in model-agnostic explanations of black-box machine learning...
research
∙
11/17/2016
Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariance
At the core of interpretable machine learning is the question of whether...
research
∙
06/16/2016
Model-Agnostic Interpretability of Machine Learning
Understanding why machine learning models behave the way they do empower...
research
∙
02/16/2016