Robuta

https://openreview.net/forum?id=xbs9ztfuQe Spurious Correlations and Where to Find Them | OpenReview Spurious correlations occur when a model learns unreliable features from the data and are a well-known drawback of data-driven learning. Although there are... where to find themspurious correlationsopenreview https://openreview.net/forum?id=Utjw2z1ale&referrer=%5Bthe%20profile%20of%20Akshay%20S%20Chaudhari%5D(%2Fprofile%3Fid%3D~Akshay_S_Chaudhari1) Identifying Spurious Correlations using Counterfactual Alignment | OpenReview Models driven by spurious correlations often yield poor generalization performance. We propose the counterfactual (CF) alignment method to detect and quantify... spurious correlationsidentifyingusingcounterfactualalignment https://openreview.net/forum?id=CmVApdsdVx Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias... Learning models have been shown to rely on spurious correlations between non-predictive features and the associated labels in the training data, with negative... spurious correlationshigh dimensional https://aclanthology.org/2025.findings-emnlp.1290/ Mitigating Spurious Correlations via Counterfactual Contrastive Learning - ACL Anthology Fengxiang Cheng, Chuan Zhou, Xiang Li, Alina Leidinger, Haoxuan Li, Mingming Gong, Fenrong Liu, Robert Van Rooij. Findings of the Association for Computational... spurious correlationscontrastive learningmitigatingviacounterfactual https://openreview.net/forum?id=8nnaDv9dUli Selection Bias Induced Spurious Correlations in Large Language Models | OpenReview Dataset selection bias can cause two unconditionally independent variables to become dependent, thus inducing spurious correlations in real-world inference... large language modelsselection biasspurious correlationsinducedopenreview https://openreview.net/forum?id=EEeVYfXor5 Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations |... Machine learning models are known to learn spurious correlations, i.e., features that have strong correlations with class labels but no causal relationship.... out ofspurious correlationsimprovingrobustness https://openreview.net/forum?id=xmllRK5QWi Elastic Representation: Mitigating Spurious Correlations for Group Robustness | OpenReview Deep learning models can suffer from severe performance degradation when relying on spurious correlations between input features and labels, making the models... spurious correlationselasticrepresentationmitigatinggroup https://openreview.net/forum?id=C9CSaTR1iA In-context Learning in Presence of Spurious Correlations | OpenReview Large language models exhibit a remarkable capacity for in-context learning, where they learn to solve tasks given a few examples. Recent work has shown that... in context learningspurious correlationspresenceopenreview https://tylervigen.com/spurious-correlations Spurious Correlations Correlation is not causation: thousands of charts of real data showing actual correlations between ridiculous variables. spuriouscorrelations https://www.tylervigen.com/spurious-correlations Spurious Correlations Correlation is not causation: thousands of charts of real data showing actual correlations between ridiculous variables. spuriouscorrelations https://openreview.net/forum?id=9mJXDcr17V Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations |... Changes in the data distribution at test time can have deleterious effects on the performance of predictive models $p(y|x)$. We consider situations where there... beyondinvariancetesttimelabel https://openreview.net/forum?id=8vo1YSAt6g&referrer=%5Bthe%20profile%20of%20Mahdi%20Ghaznavi%5D(%2Fprofile%3Fid%3D~Mahdi_Ghaznavi1) Exploiting What Trained Models Learn for Making Them Robust to Spurious Correlations without Group... Classifiers trained with Empirical Risk Minimization (ERM) often rely on spurious correlations, degrading performance on underrepresented groups and... https://arxiv.org/abs/2308.00473 [2308.00473] Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations? Abstract page for arXiv paper 2308.00473: Is Last Layer Re-Training Truly Sufficient for Robustness to Spurious Correlations? https://arxiv.org/abs/2407.14974 [2407.14974] Out of Spuriousity: Improving Robustness to Spurious Correlations without Group... Abstract page for arXiv paper 2407.14974: Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations out of https://openreview.net/forum?id=eHzIwAhj06 The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations |... Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups. In this paper,... the groupis inrobustness https://books2read.com/b/bw17PO Griffin and the Spurious Correlations Griffin and the Spurious Correlations by Krista Wallace griffinspuriouscorrelations https://openreview.net/forum?id=XkEp70qckE Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets |... This study investigates the self-rationalization framework constructed with a cooperative game, where a generator initially extracts the most informative... the risk https://www.wnycstudios.org/podcasts/otm/articles/spurious-correlations Deaths by Swimming Pool Drowning vs. Nicholas Cage Films and Other Spurious Correlations | On the... It is by now an age old adage that "correlation doesn't equal causation," but the internet just loves stories that make spurious correlations. Just yesterday...