No article text was recorded for this version.
spurious feature isolation
Version 1 of 164 papers73 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Environment Inference for Invariant Learning
- Blog: Repeated Environment Inference for Invariant Learning
- Blog: Difficulty-Based Sampling for Debiased Contrastive Representation Learning
- Blog: IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models
- Blog: Learning from others' mistakes: Avoiding dataset biases without modeling them
- Blog: Environment Inference for Invariant Learning
- Blog: Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
- Blog: Bias Amplification Enhances Minority Group Performance
- Blog: Probing Neural Network Comprehension of Natural Language Arguments
- Blog: Class-Conditional Distribution Balancing for Group Robust Classification
- Blog: Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual
- Blog: Debiasing Masks: A New Framework for Shortcut Mitigation in NLU
- Blog: Hypothesis Only Baselines in Natural Language Inference
- Blog: Partial-input baselines show that NLI models can ignore context, but they don't
- Blog: Towards Debiasing NLU Models from Unknown Biases
- Blog: Fighting Bias With Bias: Promoting Model Robustness by Amplifying Dataset Biases
- Blog: Curriculum Debiasing: Toward Robust Parameter-Efficient Fine-Tuning Against Dataset Biases
- Blog: Mitigating Shortcut Learning with InterpoLated Learning
- Blog: End-to-End Bias Mitigation by Modelling Biases in Corpora
- Blog: Debiasing Multimodal Models via Causal Information Minimization
- Blog: Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers
- Blog: Benchmarking Spurious Bias in Few-Shot Image Classifiers
- Blog: The Pitfalls of Memorization: When Memorization Hinders Generalization
- Blog: Echoes: Unsupervised Debiasing via Pseudo-bias Labeling in an Echo Chamber
- Blog: Denoising after Entropy-Based Debiasing a Robust Training Method for Dataset Bias with Noisy Labels
- Blog: Annotation Artifacts in Natural Language Inference Data
- Blog: How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics
- Blog: Mitigating Spurious Correlations via Disagreement Probability
- Blog: Improving QA Generalization by Concurrent Modeling of Multiple Biases
- Blog: BiasAdv: Bias-Adversarial Augmentation for Model Debiasing
- Blog: Adversarial Filters of Dataset Biases
- Blog: Towards Debiasing DNN Models from Spurious Feature Influence
- Blog: Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers
- Blog: Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
- Blog: Learning from Failure: De-biasing Classifier from Biased Classifier
- Blog: Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns
- Blog: Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers
- Blog: Federated Self-Explaining GNNs with Anti-shortcut Augmentations
- Blog: Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques
- Blog: LMU-BioNLP at SemEval-2024 Task 2: Large Diverse Ensembles for Robust Clinical NLI
- Blog: Self-Supervised Debiasing Using Low Rank Regularization
- Blog: MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge
- Blog: Signal Is Harder To Learn Than Bias: Debiasing with Focal Loss
- Blog: Shortcutted Commonsense: Data Spuriousness in Deep Learning of Commonsense Reasoning
- Blog: Towards Human-Understandable Multi-Dimensional Concept Discovery
- Blog: Selective Query-Guided Debiasing for Video Corpus Moment Retrieval
- Blog: Improving Bias Mitigation through Bias Experts in Natural Language Understanding
- Blog: MassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery
- Blog: A survey of methods for revealing and overcoming weaknesses of data-driven Natural Language Understanding
- Blog: Mitigating Dataset Bias by Using Per-Sample Gradient
- Blog: Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models
- Blog: AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
- Blog: How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning
- Blog: Fairness-Aware Vision Transformer via Debiased Self-Attention
- Blog: Counterfactual Debiasing for Fact Verification
- Blog: Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness
- Blog: Leveraging Sparse Linear Layers for Debuggable Deep Networks
- Blog: A guide to the dataset explosion in QA, NLI, and commonsense reasoning
- Blog: When Does Group Invariant Learning Survive Spurious Correlations?
- Blog: SelecMix: Debiased Learning by Contradicting-pair Sampling
Showing 60 of 64 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_spurious_feature_isolation_dfad2928,
title = {spurious feature isolation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/spurious-feature-isolation/rdr_dfad2928b45c423a8dece1b0f6cfe031},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_spurious_feature_isolation_dfad2928_v1,
title = {spurious feature isolation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/spurious-feature-isolation/rdr_dfad2928b45c423a8dece1b0f6cfe031/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}