# Towards Debiasing NLU Models from Unknown Biases

arXiv: https://arxiv.org/abs/2009.12303 · HTML: https://mlsanity.com/paper/2009.12303/

## Key facts

- Cited by 116 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 30 of 116)

- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence](https://mlsanity.com/paper/2103.08541/) (2021)
- [Measure and Improve Robustness in NLP Models: A Survey](https://mlsanity.com/paper/2112.08313/) (2021)
- [A Survey on Fairness in Large Language Models](https://mlsanity.com/paper/2308.10149/) (2023)
- [Shortcut Learning of Large Language Models in Natural Language Understanding](https://mlsanity.com/paper/2208.11857/) (2022)
- [Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization](https://mlsanity.com/paper/2105.05612/) (2021)
- [Distilling Model Failures as Directions in Latent Space](https://mlsanity.com/paper/2206.14754/) (2022)
- [Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models](https://mlsanity.com/paper/2103.06922/) (2021)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics](https://mlsanity.com/paper/2110.01518/) (2021)
- [Fool Me Twice: Entailment from Wikipedia Gamification](https://mlsanity.com/paper/2104.04725/) (2021)
- [Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters](https://mlsanity.com/paper/2204.07447/) (2022)
- [An Investigation of the (In)effectiveness of Counterfactually Augmented Data](https://mlsanity.com/paper/2107.00753/) (2021)
- [Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning](https://mlsanity.com/paper/2507.16795/) (2025)
- [A Survey of Small Language Models](https://mlsanity.com/paper/2410.20011/) (2024)
- [On Guiding Visual Attention with Language Specification](https://mlsanity.com/paper/2202.08926/) (2022)
- [Modeling the Second Player in Distributionally Robust Optimization](https://mlsanity.com/paper/2103.10282/) (2021)
- [Supervising Model Attention with Human Explanations for Robust Natural Language Inference](https://mlsanity.com/paper/2104.08142/) (2021)
- [From Shortcuts to Triggers: Backdoor Defense with Denoised PoE](https://mlsanity.com/paper/2305.14910/) (2023)
- [Training Dynamics for Text Summarization Models](https://mlsanity.com/paper/2110.08370/) (2021)
- [BARACK: Partially Supervised Group Robustness With Guarantees](https://mlsanity.com/paper/2201.00072/) (2021)
- [End-to-End Self-Debiasing Framework for Robust NLU Training](https://mlsanity.com/paper/2109.02071/) (2021)
- [A Robust Bias Mitigation Procedure Based on the Stereotype Content Model](https://mlsanity.com/paper/2210.14552/) (2022)
- [Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning](https://mlsanity.com/paper/2109.04144/) (2021)
- [BLIND: Bias Removal With No Demographics](https://mlsanity.com/paper/2212.10563/) (2022)
- [Weakly Supervised Detection of Hallucinations in LLM Activations](https://mlsanity.com/paper/2312.02798/) (2023)

## Abstract (arXiv)

NLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task. Recently proposed debiasing methods are shown to be effective in mitigating this tendency. However, these methods rely on a major assumption that the types of bias should be known a-priori, which limits their application to many NLU tasks and datasets. In this work, we present the first step to bridge this gap by introducing a self-debiasing framework that prevents models from mainly utilizing biases without knowing them in advance. The proposed framework is general and complementary to the existing debiasing methods. We show that it allows these existing methods to retain the improvement on the challenge datasets (i.e., sets of examples designed to expose models' reliance on biases) without specifically targeting certain biases. Furthermore, the evaluation suggests that applying the framework results in improved overall robustness.