Research map / Label-efficient and robust learning / Recognition and long-tail
Counterfactual Invariance to Spurious Correlations in Text Classification
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use conditional MMD penalty (matching anti-causal structure) instead of marginal MMD (ablation) | BERT counterfactual-invariance regularizer · Synthetic anti-causal Amazon reviews | predicted label flip rate: 2.8% -> 1.4% | Helped |
| add marginal MMD penalty on anti-causal data (mismatched) (ablation) | BERT · Natural anti-causal product reviews | sensitivity to perturbation | Hurt |
| add matching-structure MMD penalty | BERT · Natural product reviews, domain shift | out-of-domain accuracy | Helped |
| add conditional MMD penalty | BERT · MNLI | worst-group accuracy | Helped |
| add marginal MMD penalty on anti-causal MNLI (ablation) | BERT · MNLI | worst-group accuracy | No clear effect |
Closest papers by meaning
- Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models (ICLR 2024 · similarity 0.86)
- Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization (ICML 2025 · similarity 0.83)
- Gumbel Counterfactual Generation From Language Models (ICLR 2025 · similarity 0.83)
- Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors (ICML 2025 · similarity 0.83)
- Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation (ICML 2024 · similarity 0.83)
- Counterfactual Generative Modeling with Variational Causal Inference (ICLR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.