Machine learning models are increasingly utilized across impactful domai...
With the increased deployment of machine learning models in various
real...
Machine learning models often need to be robust to noisy input data. The...
Chain-of-thought (CoT) prompting has been shown to empirically improve t...
The Right to Explanation is an important regulatory principle that allow...
This work addresses the challenge of providing consistent explanations f...
The Right to Explanation and the Right to be Forgotten are two important...
As predictive models are increasingly being employed to make consequenti...
Off-policy Evaluation (OPE) methods are crucial tools for evaluating pol...
As post hoc explanations are increasingly used to understand the behavio...
Machine Learning (ML) models are increasingly used to make critical deci...
While several types of post hoc explanation methods (e.g., feature
attri...
The highly non-linear nature of deep neural networks causes them to be
s...
Predictive models are increasingly used to make various consequential
de...
Despite the plethora of post hoc model explanation methods, the basic
pr...
As post hoc explanation methods are increasingly being leveraged to expl...
As attribution-based explanation methods are increasingly used to establ...
As machine learning (ML) models are increasingly being deployed in
high-...
As practitioners increasingly deploy machine learning models in critical...
As various post hoc explanation methods are increasingly being leveraged...
In situations where explanations of black-box models may be useful, the
...
As machine learning models are increasingly used in critical decision-ma...
Counterfactual explanations and adversarial examples have emerged as cri...
As Graph Neural Networks (GNNs) are increasingly employed in real-world
...
Counterfactual explanations are emerging as an attractive option for
pro...
Machine learning models are often trained on data from one distribution ...
As predictive models are increasingly being deployed in high-stakes deci...
As the representations output by Graph Neural Networks (GNNs) are
increa...
As machine learning black boxes are increasingly being deployed in criti...
As predictive models are being increasingly deployed to make a variety o...
Ranking algorithms are being widely employed in various online hiring
pl...
As machine learning black boxes are increasingly being deployed in real-...
As machine learning (ML) models are increasingly being employed to assis...
As machine learning models are increasingly deployed in high-stakes doma...
Domains where supervised models are deployed often come with task-specif...
As predictive models are increasingly being deployed in high-stakes
deci...
As local explanations of black box models are increasingly being employe...
Several social interventions (e.g., suicide and HIV prevention) leverage...
As machine learning black boxes are increasingly being deployed in criti...
As machine learning black boxes are increasingly being deployed in domai...
We propose Black Box Explanations through Transparent Approximations (BE...
Predictive models deployed in the real world may assign incorrect labels...
Decision makers, such as doctors and judges, make crucial decisions such...