# End-to-End Self-Debiasing Framework for Robust NLU Training

arXiv: https://arxiv.org/abs/2109.02071 · HTML: https://mlsanity.com/paper/2109.02071/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 5 Sep 2021.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference](https://mlsanity.com/paper/1808.05326/) (2018)
- [Hypothesis Only Baselines in Natural Language Inference](https://mlsanity.com/paper/1805.01042/) (2018)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [Towards Debiasing Fact Verification Models](https://mlsanity.com/paper/1908.05267/) (2019)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [End-to-End Bias Mitigation by Modelling Biases in Corpora](https://mlsanity.com/paper/1909.06321/) (2019)
- [The Right Tool for the Job: Matching Model and Instance Complexities](https://mlsanity.com/paper/2004.07453/) (2020)
- [Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual](https://mlsanity.com/paper/1908.10763/) (2019)
- [Towards Debiasing NLU Models from Unknown Biases](https://mlsanity.com/paper/2009.12303/) (2020)
- [Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance](https://mlsanity.com/paper/2005.00315/) (2020)
- [Learning from others' mistakes: Avoiding dataset biases without modeling them](https://mlsanity.com/paper/2012.01300/) (2020)
- [Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles](https://mlsanity.com/paper/2011.03856/) (2020)
- [Evaluating Compositionality in Sentence Embeddings](https://mlsanity.com/paper/1802.04302/) (2018)
- [Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects](https://mlsanity.com/paper/1906.08430/) (2019)
- [Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition](https://mlsanity.com/paper/2107.11610/) (2021)
- [Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures](https://mlsanity.com/paper/2010.12510/) (2020)

## Built on by (most cited first, 24 of 24)

- [Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets](https://mlsanity.com/paper/2203.12942/) (2022)
- [From Shortcuts to Triggers: Backdoor Defense with Denoised PoE](https://mlsanity.com/paper/2305.14910/) (2023)
- [LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs](https://mlsanity.com/paper/2408.08656/) (2024)
- [RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation](https://mlsanity.com/paper/2109.10164/) (2021)
- [Feature-Level Debiased Natural Language Understanding](https://mlsanity.com/paper/2212.05421/) (2022)
- [Robust Natural Language Understanding with Residual Attention Debiasing](https://mlsanity.com/paper/2305.17627/) (2023)
- [A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models](https://mlsanity.com/paper/2210.05211/) (2022)
- [EqualizeIR: Mitigating Linguistic Biases in Retrieval Models](https://mlsanity.com/paper/2504.07115/) (2025)
- [Adversarial Attacks Against Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2509.08463/) (2025)
- [How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding](https://mlsanity.com/paper/2109.05696/) (2021)
- [A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension](https://mlsanity.com/paper/2209.01824/) (2022)
- [DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade](https://mlsanity.com/paper/2305.14751/) (2023)
- [A Simple yet Effective Self-Debiasing Framework for Transformer Models](https://mlsanity.com/paper/2306.01907/) (2023)
- [Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection](https://mlsanity.com/paper/2505.20209/) (2025)
- [Explanation based Bias Decoupling Regularization for Natural Language Inference](https://mlsanity.com/paper/2404.13390/) (2024)
- [Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities](https://mlsanity.com/paper/2302.02852/) (2023)
- [Improving Bias Mitigation through Bias Experts in Natural Language Understanding](https://mlsanity.com/paper/2312.03577/) (2023)
- [Mitigating Shortcut Learning with InterpoLated Learning](https://mlsanity.com/paper/2507.05527/) (2025)
- [Knowledge Distillation with Noisy Labels for Natural Language Understanding](https://mlsanity.com/paper/2109.10147/) (2021)
- [Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals](https://mlsanity.com/paper/2305.13535/) (2023)
- [Self-Supervised Position Debiasing for Large Language Models](https://mlsanity.com/paper/2401.01218/) (2024)
- [Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding](https://mlsanity.com/paper/2406.12060/) (2024)
- [Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology](https://mlsanity.com/paper/2409.19766/) (2024)
- [FairFlow: Mitigating Dataset Biases through Undecided Learning](https://mlsanity.com/paper/2503.17632/) (2025)

## Abstract (arXiv)

Existing Natural Language Understanding (NLU) models have been shown to incorporate dataset biases leading to strong performance on in-distribution (ID) test sets but poor performance on out-of-distribution (OOD) ones. We introduce a simple yet effective debiasing framework whereby the shallow representations of the main model are used to derive a bias model and both models are trained simultaneously. We demonstrate on three well studied NLU tasks that despite its simplicity, our method leads to competitive OOD results. It significantly outperforms other debiasing approaches on two tasks, while still delivering high in-distribution performance.