English
Related papers

Related papers: Identifying the Source of Vulnerability in Explana…

200 papers

Post-hoc explanations are widely used to justify, contest, and review automated decisions in high-stakes domains such as lending, employment, and healthcare. Among these methods, SHAP is often treated as providing a reliable account of…

Machine Learning · Computer Science 2026-01-27 Hyunseung Hwang , Seungeun Lee , Lucas Rosenblatt , Steven Euijong Whang , Julia Stoyanovich

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Computation and Language · Computer Science 2023-05-04 Ruochen Zhao , Shafiq Joty , Yongjie Wang , Tan Wang

As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the behaviors of these black boxes. However, existing…

Machine Learning · Computer Science 2020-11-13 Himabindu Lakkaraju , Nino Arsov , Osbert Bastani

In this article, we present a leap-forward expansion to the study of explainability in neural networks by considering explanations as answers to abstract reasoning-based questions. With $P$ as the prediction from a neural network, these…

Machine Learning · Computer Science 2022-02-25 Ghassan AlRegib , Mohit Prabhushankar

Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both of these purposes. Namely, we show that explanations can be…

Advances in the effectiveness of machine learning models have come at the cost of enormous complexity resulting in a poor understanding of how they function. Local surrogate methods have been used to approximate the workings of these…

Machine Learning · Computer Science 2025-01-16 Christopher Burger , Charles Walter

Deep neural networks, while powerful for image classification, often operate as "black boxes," complicating the understanding of their decision-making processes. Various explanation methods, particularly those generating saliency maps, aim…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Tristan Gomez , Harold Mouchère

Robustness and counterfactual bias are usually evaluated on a test dataset. However, are these evaluations robust? If the test dataset is perturbed slightly, will the evaluation results keep the same? In this paper, we propose a "double…

Computation and Language · Computer Science 2021-04-13 Chong Zhang , Jieyu Zhao , Huan Zhang , Kai-Wei Chang , Cho-Jui Hsieh

Predictive variability due to data ambiguities has typically been addressed via construction of dedicated models with built-in probabilistic capabilities that are trained to predict uncertainty estimates as variables of interest. These…

Machine Learning · Computer Science 2023-08-04 Katarína Tóthová , Ľubor Ladický , Daniel Thul , Marc Pollefeys , Ender Konukoglu

To verify and validate networks, it is essential to gain insight into their decisions, limitations as well as possible shortcomings of training data. In this work, we propose a post-hoc, optimization based visual explanation method, which…

Computer Vision and Pattern Recognition · Computer Science 2019-08-08 Jörg Wagner , Jan Mathias Köhler , Tobias Gindele , Leon Hetzel , Jakob Thaddäus Wiedemer , Sven Behnke

We present a model-agnostic algorithm for generating post-hoc explanations and uncertainty intervals for a machine learning model when only a static sample of inputs and outputs from the model is available, rather than direct access to the…

Machine Learning · Computer Science 2023-06-27 Surin Ahn , Justin Grana , Yafet Tamene , Kristian Holsheimer

As black box explanations are increasingly being employed to establish model credibility in high-stakes settings, it is important to ensure that these explanations are accurate and reliable. However, prior work demonstrates that…

Machine Learning · Computer Science 2021-11-09 Dylan Slack , Sophie Hilgard , Sameer Singh , Himabindu Lakkaraju

There have been several post-hoc explanation approaches developed to explain pre-trained black-box neural networks. However, there is still a gap in research efforts toward designing neural networks that are inherently explainable. In this…

Computer Vision and Pattern Recognition · Computer Science 2022-07-01 Subash Khanal , Benjamin Brodie , Xin Xing , Ai-Ling Lin , Nathan Jacobs

We address the problem of uncertainty calibration. While standard deep neural networks typically yield uncalibrated predictions, calibrated confidence scores that are representative of the true likelihood of a prediction can be achieved…

Machine Learning · Computer Science 2021-06-24 Christian Tomani , Sebastian Gruber , Muhammed Ebrar Erdem , Daniel Cremers , Florian Buettner

Recent work in Natural Language Processing has focused on developing approaches that extract faithful explanations, either via identifying the most important tokens in the input (i.e. post-hoc explanations) or by designing inherently…

Computation and Language · Computer Science 2022-03-02 George Chrysostomou , Nikolaos Aletras

Perturbation-based explanations are widely utilized to enhance the transparency of machine-learning models in practice. However, their reliability is often compromised by the unknown model behavior under the specific perturbations used.…

Machine Learning · Computer Science 2025-11-14 Thomas Decker , Volker Tresp , Florian Buettner

Uncertainty quantification is critical in safety-sensitive applications but is often omitted from off-the-shelf neural networks due to adverse effects on predictive performance. Retrofitting uncertainty estimates post-hoc typically requires…

Machine Learning · Computer Science 2025-06-03 Lennart Bramlage , Cristóbal Curio

For applications of machine learning in critical decisions, explainability is a primary concern, and often a regulatory requirement. Local linear methods for generating explanations, such as LIME and SHAP, have been criticized for being…

Machine Learning · Computer Science 2026-03-25 Joseph L. Breeden

Despite excellent performance of deep neural networks (DNNs) in image classification, detection, and prediction, characterizing how DNNs make a given decision remains an open problem, resulting in a number of interpretability methods.…

Machine Learning · Computer Science 2023-09-13 Lennart Brocki , Neo Christopher Chung

Recent years have witnessed the emergence of a variety of post-hoc interpretations that aim to uncover how natural language processing (NLP) models make predictions. Despite the surge of new interpretation methods, it remains an open…

Computation and Language · Computer Science 2022-04-04 Fan Yin , Zhouxing Shi , Cho-Jui Hsieh , Kai-Wei Chang