# Identifying Spurious Correlations and Correcting them with an Explanation-based Learning

Source: [Identifying Spurious Correlations and Correcting them with an Explanation-based Learning](<https://www.sota2.com/research/paper/68fa6e1e1e209131cea3dec8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:50:11.375Z

Authors: Misgina Tsighe Hagos, Kathleen M. Curran, Brian Mac Namee

Published: 2022-11-15T16:34:53.000Z

## Abstract

Identifying spurious correlations learned by a trained model is at the core of refining a trained model and building a trustworthy model. We present a simple method to identify spurious correlations that have been learned by a model trained for image classification problems. We apply image-level perturbations and monitor changes in certainties of predictions made using the trained model. We demonstrate this approach using an image classification dataset that contains images with synthetically generated spurious regions and show that the trained model was overdependent on spurious regions. Moreover, we remove the learned spurious correlations with an explanation based learning approach.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.08285>)

[PDF](<https://arxiv.org/pdf/2211.08285.pdf>)