168 citations · 871 across the 72 of their papers we have counts for
45 papers · 1 filter
Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
Michal Moshkovitz, Suraj Srinivas, Lesia Semenova +7
Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice,…
Generalized Group Data Attribution
Dan Ley, Suraj Srinivas, Shichang Zhang +2
Data Attribution (DA) methods quantify the influence of individual training data points on model outputs and have broad applications such as explainability, data selection, and noi…
Learning Recourse Costs from Pairwise Feature Comparisons
Kaivalya Rawal, Himabindu Lakkaraju
This paper presents a novel technique for incorporating user input when learning and inferring user preferences. When trying to provide users of black-box machine learning models w…
Interpretability Needs a New Paradigm
Andreas Madsen, Himabindu Lakkaraju, Siva Reddy +1
Interpretability is the study of explaining models in understandable terms to humans. At present, interpretability is divided into two paradigms: the intrinsic paradigm, which beli…
Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
Elita Lobo, Harvineet Singh, Marek Petrik +2
Off-policy Evaluation (OPE) methods are a crucial tool for evaluating policies in high-stakes domains such as healthcare, where exploration is often infeasible, unethical, or expen…
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
Usha Bhalla, Alex Oesterling, Suraj Srinivas +2
CLIP embeddings have demonstrated remarkable performance across a wide range of multimodal applications. However, these high-dimensional, dense vector representations are not easil…
In-Context Unlearning: Language Models as Few Shot Unlearners
Martin Pawelczyk, Seth Neel, Himabindu Lakkaraju
Machine unlearning, the study of efficiently removing the impact of specific training instances on a model, has garnered increased attention in recent years due to regulatory guide…
On the Trade-offs between Adversarial Robustness and Actionable Explanations
Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju
As machine learning models are increasingly being employed in various high-stakes settings, it becomes important to ensure that predictions of these models are not only adversarial…
Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakage
Catherine Huang, Chelse Swoopes, Christina Xiao +2
Machine learning models are increasingly utilized across impactful domains to predict individual outcomes. As such, many models provide algorithmic recourse to individuals who rece…
Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
Usha Bhalla, Suraj Srinivas, Himabindu Lakkaraju
With the increased deployment of machine learning models in various real-world applications, researchers and practitioners alike have emphasized the need for explanations of model…
Characterizing Data Point Vulnerability via Average-Case Robustness
Tessa Han, Suraj Srinivas, Himabindu Lakkaraju
Studying the robustness of machine learning models is important to ensure consistent model behaviour across real-world settings. To this end, adversarial robustness is a standard f…
Consistent Explanations in the Face of Model Indeterminacy via Ensembling
Dan Ley, Leonard Tang, Matthew Nazari +3
This work addresses the challenge of providing consistent explanations for predictive models in the presence of model indeterminacy, which arises due to the existence of multiple (…
On Minimizing the Impact of Dataset Shifts on Actionable Explanations
Anna P. Meyer, Dan Ley, Suraj Srinivas +1
The Right to Explanation is an important regulatory principle that allows individuals to request actionable explanations for algorithmic decisions. However, several technical chall…
Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness
Suraj Srinivas, Sebastian Bordt, Hima Lakkaraju
One of the remarkable properties of robust computer vision models is that their input-gradients are often aligned with human perception, referred to in the literature as perceptual…
On the Privacy Risks of Algorithmic Recourse
Martin Pawelczyk, Himabindu Lakkaraju, Seth Neel
As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to…
Towards Robust Off-Policy Evaluation via Human Inputs
Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez +1
Off-policy Evaluation (OPE) methods are crucial tools for evaluating policies in high-stakes domains such as healthcare, where direct deployment is often infeasible, unethical, or…
Evaluating Explainability for Graph Neural Networks
Chirag Agarwal, Owen Queen, Himabindu Lakkaraju +1
As post hoc explanations are increasingly used to understand the behavior of graph neural networks (GNNs), it becomes crucial to evaluate the quality and reliability of GNN explana…
TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations
Dylan Slack, Satyapriya Krishna, Himabindu Lakkaraju +1
Machine Learning (ML) models are increasingly used to make critical decisions in real-world applications, yet they have become more complex, making them harder to understand. To th…
Fairness via Explanation Quality: Evaluating Disparities in the Quality of Post hoc Explanations
Jessica Dai, Sohini Upadhyay, Ulrich Aivodji +2
As post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to ensure that the quality of the resulting…
OpenXAI: Towards a Transparent Evaluation of Model Explanations
Chirag Agarwal, Dan Ley, Satyapriya Krishna +6
While several types of post hoc explanation methods have been proposed in recent literature, there is very little work on systematically benchmarking these methods. Here, we introd…
Efficiently Training Low-Curvature Neural Networks
Suraj Srinivas, Kyle Matoba, Himabindu Lakkaraju +1
The highly non-linear nature of deep neural networks causes them to be susceptible to adversarial examples and have unstable gradients which hinders interpretability. However, exis…
A Human-Centric Take on Model Monitoring
Murtuza N Shergadwala, Himabindu Lakkaraju, Krishnaram Kenthapadi
Predictive models are increasingly used to make various consequential decisions in high-stakes domains such as healthcare, finance, and policy. It becomes critical to ensure that t…
Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations
Tessa Han, Suraj Srinivas, Himabindu Lakkaraju
A critical problem in the field of post hoc explainability is the lack of a common foundational goal among methods. For example, some methods are motivated by function approximatio…
Rethinking Stability for Attribution-based Explanations
Chirag Agarwal, Nari Johnson, Martin Pawelczyk +4
As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are st…