Image de couverture de livre

Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gilligan-Lee, Ciarán M., Egan, Joseph, Zhu, Yuchen, O'Riordan, Michael
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Local Interference: Removing Interference Bias in Semi-Parametric Causal Models
par: O'Riordan, Michael, et autres
Publié: (2025)

Spillover Detection for Donor Selection in Synthetic Control Models
par: O'Riordan, Michael, et autres
Publié: (2024)

Contrastive representations of high-dimensional, structured treatments
par: Andreu, Oriol Corcoll, et autres
Publié: (2024)

The Hardness of Validating Observational Studies with Experimental Data
par: Fawkes, Jake, et autres
Publié: (2025)

Training on Plausible Counterfactuals Removes Spurious Correlations
par: Sadiku, Shpresim, et autres
Publié: (2025)

Higher-Order Singular-Value Derivatives of Rectangular Real Matrices
par: Luo, Róisín, et autres
Publié: (2025)

Unsupervised Concept Discovery Mitigates Spurious Correlations
par: Arefin, Md Rifat, et autres
Publié: (2024)

Removing Spurious Correlation from Neural Network Interpretations
par: Fotouhi, Milad, et autres
Publié: (2024)

ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations
par: Chakraborty, Rwiddhi, et autres
Publié: (2024)

Quantum oracles give an advantage for identifying classical counterfactuals
par: Gilligan-Lee, Ciarán M., et autres
Publié: (2025)

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
par: Chen, Yiwei, et autres
Publié: (2025)

Optimization-Induced Dynamics of Lipschitz Continuity in Neural Networks
par: Luo, Róisín, et autres
Publié: (2025)

Nature versus nurture in galaxy formation: the effect of environment on star formation with causal machine learning
par: Mucesh, Sunil, et autres
Publié: (2024)

Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
par: Elisha, Yehonatan, et autres
Publié: (2026)

Mitigating Spurious Correlations via Disagreement Probability
par: Han, Hyeonggeun, et autres
Publié: (2024)

Reassessing the Validity of Spurious Correlations Benchmarks
par: Bell, Samuel J., et autres
Publié: (2024)

Identifying Spurious Correlations using Counterfactual Alignment
par: Cohen, Joseph Paul, et autres
Publié: (2023)

IMU-Enhanced EEG Motion Artifact Removal with Fine-Tuned Large Brain Models
par: Zhang, Yuhong, et autres
Publié: (2025)

Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations
par: Le, Phuong Quynh, et autres
Publié: (2024)

Public Sector Open Source Program Offices - Archetypes for how to Grow (Common) Institutional Capabilities
par: Linåker, Johan, et autres
Publié: (2026)

Severing Spurious Correlations with Data Pruning
par: Mulchandani, Varun, et autres
Publié: (2025)

In-context Learning in Presence of Spurious Correlations
par: Harutyunyan, Hrayr, et autres
Publié: (2024)

Revisiting Spurious Correlation in Domain Generalization
par: Qin, Bin, et autres
Publié: (2024)

An Iterative Development of a Training Programme in the Use of the Internet as an Information Source and Publishing Mechanism.
par: O'Riordan, Gobnait
Publié: (1996)

SSF-RPOA: deep-rooted problems, great expectations
par: O’Riordan, Brian
Publié: (2018)

Europe: new, but long overdue
par: O’Riordan, Brian
Publié: (2016)

Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness
par: Park, Subeen, et autres
Publié: (2025)

Investigating the Robustness of Subtask Distillation under Spurious Correlation
par: Chormai, Pattarawat, et autres
Publié: (2026)

Elastic Representation: Mitigating Spurious Correlations for Group Robustness
par: Wen, Tao, et autres
Publié: (2025)

Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective
par: Zhou, Yuqing, et autres
Publié: (2024)

Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations
par: Zhang, Michael, et autres
Publié: (2022)

Detecting the hidden population of low-mass haloes in strong lenses
par: O'Riordan, Conor M.
Publié: (2025)

The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
par: LaBonte, Tyler, et autres
Publié: (2024)

Improving Group Robustness on Spurious Correlation via Evidential Alignment
par: Ye, Wenqian, et autres
Publié: (2025)

Does Weak-to-strong Generalization Happen under Spurious Correlations?
par: Liu, Chenruo, et autres
Publié: (2025)

Spurious Correlations in Concept Drift: Can Explanatory Interaction Help?
par: Lalletti, Cristiana, et autres
Publié: (2024)

Complexity Matters: Dynamics of Feature Learning in the Presence of Spurious Correlations
par: Qiu, GuanWen, et autres
Publié: (2024)

State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
par: Kang, Wonjun, et autres
Publié: (2025)

NeuronTune: Towards Self-Guided Spurious Bias Mitigation
par: Zheng, Guangtao, et autres
Publié: (2025)

Parameter-Efficient Fine-Tuning of State Space Models
par: Galim, Kevin, et autres
Publié: (2024)