[ICML 2023] Change is Hard: A Closer Look at Subpopulation Shift

Search lots of data sets for spurious correlations

Implementation of the EMNLP 2020 paper "Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition".

Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet

[NeurIPS 2023] Understanding and Improving Feature Learning for Out-of-Distribution Generalization

[Nature Medicine] The Limits of Fair Medical Imaging AI In Real-World Generalization

Official Repository for Spurious Memorization - Nature Communications 2025

Understanding Rare Spurious Correlations in Neural Network

[ICCV25] TD-DETR: The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning

Carloni, G., Tsaftaris, S. A., & Colantonio, S. (2024). CROCODILE: Causality aids RObustness via COntrastive DIsentangled LEarning @ MICCAI 2024 UNSURE Workshop

Which Shortcut Solution Do Question Answering Models Prefer to Learn? (AAAI2023)

The official repository for "Training Debiased Subnetworks with Contrastive Weight Pruning"

How to detect spurious and hidden correlations in R using linear models

Spurious correlation simulator

This repository contains the code for the paper "Disentangling representations of retinal images with generative models".

Official code of our paper "Autoencoder based approach for the mitigation of spurious correlations on YOLOv5"

Mitigating Spurious Correlations for Self-supervised Recommendation

Solution for the Third Challenge of the First Phase in the Rayan International AI Contest: Hierarchical Group Robustness.

VISION is a framework for robust and interpretable code vulnerability detection using counterfactual data augmentation. It leverages GNNs, LLM-generated counterfactuals, and graph-based explainability to mitigate spurious correlations and improve generalization on real-world vulnerabilities (CWE-20).

This is the official implementation of our paper Robust Hate Speech Detection via Mitigating Spurious Correlations (Tiwari et al., AACL-IJCNLP 2022)