English
Related papers

Related papers: Post hoc Explanations may be Ineffective for Detec…

200 papers

Learning models have been shown to rely on spurious correlations between non-predictive features and the associated labels in the training data, with negative implications on robustness, bias and fairness. In this work, we provide a…

Machine Learning · Statistics 2025-05-29 Simone Bombari , Marco Mondelli

Large Language Models (LLMs) are so powerful that they sometimes learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on out-of-distribution data. We propose explanation-based…

Computation and Language · Computer Science 2023-06-07 Josh Magnus Ludan , Yixuan Meng , Tai Nguyen , Saurabh Shah , Qing Lyu , Marianna Apidianaki , Chris Callison-Burch

Post-hoc model-agnostic interpretation methods such as partial dependence plots can be employed to interpret complex machine learning models. While these interpretation methods can be applied regardless of model complexity, they can produce…

Machine Learning · Statistics 2022-01-24 Christoph Molnar , Giuseppe Casalicchio , Bernd Bischl

Large language models are highly sensitive to prompts, but this sensitivity is usually studied through task-relevant instructions, demonstrations, or reasoning cues. In this paper, we study a different form of prompt sensitivity: whether…

Computation and Language · Computer Science 2026-05-29 Pawel Batorski , Abtin Pourhadi , Jerzy Sarosiek , Przemyslaw Spurek , Paul Swoboda

Deep neural networks can be unreliable in the real world especially when they heavily use {\it spurious} features for their predictions. Focusing on image classifications, we define {\it core features} as the set of visual features that are…

Machine Learning · Computer Science 2022-03-29 Sahil Singla , Soheil Feizi

Models driven by spurious correlations often yield poor generalization performance. We propose the counterfactual (CF) alignment method to detect and quantify spurious correlations of black box classifiers. Our methodology is based on…

Computer Vision and Pattern Recognition · Computer Science 2025-01-16 Joseph Paul Cohen , Louis Blankemeier , Akshay Chaudhari

Acquiring and training on large-scale labeled data can be impractical due to cost constraints. Additionally, the use of small training datasets can result in considerable variability in model outcomes, overfitting, and learning of spurious…

Machine Learning · Computer Science 2025-07-08 Jiashu Tao , Reza Shokri

Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Removing such concepts is non-trivial because of a complex relationship between the concept, text…

Machine Learning · Computer Science 2023-06-21 Abhinav Kumar , Chenhao Tan , Amit Sharma

Predictive models -- learned from observational data not covering the complete data distribution -- can rely on spurious correlations in the data for making predictions. These correlations make the models brittle and hinder generalization.…

Machine Learning · Computer Science 2020-06-16 Khurram Javed , Martha White , Yoshua Bengio

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

Deep neural networks for medical image diagnosis often achieve high predictive accuracy while relying on spurious or clinically irrelevant visual cues, limiting their trustworthiness in practice. Post-hoc explanation methods are widely used…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Zubair Faruqui , Rahul Dubey

Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations. Post-hoc model-agnostic explanation methods addresses this challenge by learning a…

Machine Learning · Computer Science 2026-03-18 Sumedha Chugh , Ranjitha Prasad , Nazreen Shah

Deep learning models are known to overfit and memorize spurious features in the training dataset. While numerous empirical studies have aimed at understanding this phenomenon, a rigorous theoretical framework to quantify it is still…

Machine Learning · Statistics 2024-05-20 Simone Bombari , Marco Mondelli

Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications, where they frequently face data distributions unseen during training. Despite progress, existing…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Reihaneh Zohrabi , Hosein Hasani , Mahdieh Soleymani Baghshah , Anna Rohrbach , Marcus Rohrbach , Mohammad Hossein Rohban

Post-hoc explanation methods are widely used to interpret black-box predictions, but their generation is often computationally expensive and their reliability is not guaranteed. We propose epistemic uncertainty as a low-cost proxy for…

Artificial Intelligence · Computer Science 2026-04-01 Georgii Mikriukov , Grégoire Montavon , Marina M. -C. Höhne

Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly prone to learning spurious correlations in the training data, that may not hold at test time. In…

Machine Learning · Computer Science 2024-03-08 Yu Yang , Eric Gan , Gintare Karolina Dziugaite , Baharan Mirzasoleiman

Training the deep neural networks that dominate NLP requires large datasets. These are often collected automatically or via crowdsourcing, and may exhibit systematic biases or annotation artifacts. By the latter we mean spurious…

Computation and Language · Computer Science 2022-03-29 Pouya Pezeshkpour , Sarthak Jain , Sameer Singh , Byron C. Wallace

The presence of spurious features interferes with the goal of obtaining robust models that perform well across many groups within the population. A natural remedy is to remove spurious features from the model. However, in this work we show…

Machine Learning · Computer Science 2020-12-09 Fereshte Khani , Percy Liang

Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments. However, mitigating these correlations during pre-training for…

Machine Learning · Computer Science 2023-06-01 Yu Yang , Besmira Nushi , Hamid Palangi , Baharan Mirzasoleiman

Deep Neural Networks (DNNs) are prone to learning spurious features that correlate with the label during training but are irrelevant to the learning problem. This hurts model generalization and poses problems when deploying them in…

Machine Learning · Computer Science 2023-10-17 Nihal Murali , Aahlad Puli , Ke Yu , Rajesh Ranganath , Kayhan Batmanghelich