Image de couverture de livre

Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Jiayi, Tang, Shijie, Kaynar, Gün, Du, Shiyi, Kingsford, Carl
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

CodonMoE: DNA Language Models for mRNA Analyses
par: Du, Shiyi, et autres
Publié: (2025)

ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models
par: Zheng, Guangtao, et autres
Publié: (2025)

Shortcut Mitigation via Spurious-Positive Samples
par: Le, Phuong Quynh, et autres
Publié: (2026)

Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models
par: Zhou, Yuqing, et autres
Publié: (2024)

Mitigating Shortcut Learning with InterpoLated Learning
par: Korakakis, Michalis, et autres
Publié: (2025)

Neural Flow Samplers with Shortcut Models
par: Chen, Wuhao, et autres
Publié: (2025)

Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learning
par: Wimmer, Lisa, et autres
Publié: (2025)

Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification
par: Eshuijs, Leon, et autres
Publié: (2025)

Reasoning in Transformers -- Mitigating Spurious Correlations and Reasoning Shortcuts
par: Enström, Daniel, et autres
Publié: (2024)

A Typology for Exploring the Mitigation of Shortcut Behavior
par: Friedrich, Felix, et autres
Publié: (2022)

Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models
par: Yuan, Yu, et autres
Publié: (2024)

Gradient-based Model Shortcut Detection for Time Series Classification
par: Ibarra, Salomon, et autres
Publié: (2025)

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
par: Liu, Gongye, et autres
Publié: (2023)

Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers
par: Kuhn, Lukas, et autres
Publié: (2025)

MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers
par: Zhao, Lili, et autres
Publié: (2025)

Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
par: Yue, Linan, et autres
Publié: (2024)

Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priors
par: Du, Shiyi, et autres
Publié: (2026)

SLAP: Shortcut Learning for Abstract Planning
par: Liu, Y. Isabel, et autres
Publié: (2025)

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
par: Scimeca, Luca, et autres
Publié: (2023)

On the Foundations of Shortcut Learning
par: Hermann, Katherine L., et autres
Publié: (2023)

On Measuring Localization of Shortcuts in Deep Networks
par: Tsoy, Nikita, et autres
Publié: (2025)

Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts
par: Cai, Weilin, et autres
Publié: (2024)

Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
par: Steinmann, David, et autres
Publié: (2024)

ClearGCD: Mitigating Shortcut Learning For Robust Generalized Category Discovery
par: Lyu, Kailin, et autres
Publié: (2025)

Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning
par: Dolatabadi, Hadi M., et autres
Publié: (2024)

Shortcut to Nowhere: Demystifying Deep Spurious Regression
par: Xu, Guanrong, et autres
Publié: (2026)

Optimizing DDPM Sampling with Shortcut Fine-Tuning
par: Fan, Ying, et autres
Publié: (2023)

Neurosymbolic Reasoning Shortcuts under the Independence Assumption
par: van Krieken, Emile, et autres
Publié: (2025)

One Step Diffusion via Shortcut Models
par: Frans, Kevin, et autres
Publié: (2024)

Learning with Logical Constraints but without Shortcut Satisfaction
par: Li, Zenan, et autres
Publié: (2024)

Computationally Efficient High-Dimensional Bayesian Optimization via Variable Selection
par: Shen, Yihang, et autres
Publié: (2021)

Separating Shortcut Transition from Cross-Family OOD Failure in a Minimal Model
par: Li, Hongmin
Publié: (2026)

CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models
par: Kocak, Aysenur, et autres
Publié: (2025)

UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding
par: He, Jiaming, et autres
Publié: (2026)

Shortcut Learning Susceptibility in Vision Classifiers
par: Suhail, Pirzada, et autres
Publié: (2025)

BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
par: Marconato, Emanuele, et autres
Publié: (2024)

Learning Shortcuts: On the Misleading Promise of NLU in Language Models
par: Bihani, Geetanjali, et autres
Publié: (2024)

Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
par: Müller, Sarah, et autres
Publié: (2026)

Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
par: Wang, Xiangmeng, et autres
Publié: (2026)

Shortcut learning in geometric knot classification
par: Mihajlovic, Djordje, et autres
Publié: (2026)