86 citations · 97 across the 7 of their papers we have counts for
6 papers · 1 filter
ContextCite: Attributing Model Generation to Context
Benjamin Cohen-Wang, Harshay Shah, Kristian Georgiev +1
How do language models use information provided as context when generating a response? Can we infer whether a particular generated statement is actually grounded in the context, a…
Decomposing and Editing Predictions by Modeling Model Computation
Harshay Shah, Andrew Ilyas, Aleksander Madry
How does the internal computation of a machine learning model transform inputs into predictions? In this paper, we introduce a task called component modeling that aims to address t…
ModelDiff: A Framework for Comparing Learning Algorithms
Harshay Shah, Sung Min Park, Andrew Ilyas +1
We study the problem of (learning) algorithm comparison, where the goal is to find differences between models trained with two different learning algorithms. We begin by formalizin…
Do Input Gradients Highlight Discriminative Features?
Harshay Shah, Prateek Jain, Praneeth Netrapalli
Post-hoc gradient-based interpretability methods [Simonyan et al., 2013, Smilkov et al., 2017] that provide instance-specific explanations of model predictions are often based on a…
The Pitfalls of Simplicity Bias in Neural Networks
Harshay Shah, Kaustav Tamuly, Aditi Raghunathan +2
Several works have proposed Simplicity Bias (SB)---the tendency of standard training procedures such as Stochastic Gradient Descent (SGD) to find simple models---to justify why neu…
Number of Connected Components in a Graph: Estimation via Counting Patterns
Ashish Khetan, Harshay Shah, Sewoong Oh
Due to the limited resources and the scale of the graphs in modern datasets, we often get to observe a sampled subgraph of a larger original graph of interest, whether it is the wo…