Identifying Spurious Correlations using Counterfactual Alignment
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 counterfactual images generated with respect to one classifier being input into other classifiers to see if they also induce changes in the outputs of these classifiers. The relationship between these responses can be quantified and used to identify specific instances where a spurious correlation exists. This is validated by observing intuitive trends in face-attribute and waterbird classifiers, as well as by fabricating spurious correlations and detecting their presence, both visually and quantitatively. Furthermore, utilizing the CF alignment method, we demonstrate that we can evaluate robust optimization methods (GroupDRO, JTT, and FLAC) by detecting a reduction in spurious correlations.
Code (1)
Tasks
AttributecounterfactualSimilar Papers 제목 키워드 기반
Uninformative Input Features and Counterfactual Invariance: Two Perspectives on Spurious Correlations in Natural Language
The natural language processing community has become increasingly interested in spurious correlations, and in methods for identifying and eliminating them. Gardner et al (2021) argue that due to the compositional nature …
counterfactualDebiasing Counterfactuals In the Presence of Spurious Correlations
Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rat…
counterfactualImage GenerationExplore Spurious Correlations at the Concept Level in Language Models for Text Classification
Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness…
counterfactualIn-Context Learningtext-classificationText ClassificationBeyond Reward Hacking: Causal Rewards for Large Language Model Alignment
Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human p…
Causal InferencecounterfactualFairnessLanguage Modeling+2An Investigation of the (In)effectiveness of Counterfactually Augmented Data
While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work…
DiversityNatural Language Understanding