# Debiasing Methods in Natural Language Understanding Make Bias More Accessible

arXiv: https://arxiv.org/abs/2109.04095 · HTML: https://mlsanity.com/paper/2109.04095/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 9 Sep 2021.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (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)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Information-Theoretic Probing with Minimum Description Length](https://mlsanity.com/paper/2003.12298/) (2020)
- [Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks](https://mlsanity.com/paper/1608.04207/) (2016)
- [Towards Debiasing Fact Verification Models](https://mlsanity.com/paper/1908.05267/) (2019)
- [End-to-End Bias Mitigation by Modelling Biases in Corpora](https://mlsanity.com/paper/1909.06321/) (2019)
- [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)
- [BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance](https://mlsanity.com/paper/1911.02969/) (2019)
- [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)

## Built on by (most cited first, 17 of 17)

- [Shortcut Learning of Large Language Models in Natural Language Understanding](https://mlsanity.com/paper/2208.11857/) (2022)
- [InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models](https://mlsanity.com/paper/2410.22770/) (2024)
- [Are All Spurious Features in Natural Language Alike? An Analysis through a Causal Lens](https://mlsanity.com/paper/2210.14011/) (2022)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection](https://mlsanity.com/paper/2305.10204/) (2023)
- [BLIND: Bias Removal With No Demographics](https://mlsanity.com/paper/2212.10563/) (2022)
- [How Gender Debiasing Affects Internal Model Representations, and Why It Matters](https://mlsanity.com/paper/2204.06827/) (2022)
- [Feature-Level Debiased Natural Language Understanding](https://mlsanity.com/paper/2212.05421/) (2022)
- [Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis](https://mlsanity.com/paper/2310.00347/) (2023)
- [Looking at the Overlooked: An Analysis on the Word-Overlap Bias in Natural Language Inference](https://mlsanity.com/paper/2211.03862/) (2022)
- [Mitigating Shortcut Learning with InterpoLated Learning](https://mlsanity.com/paper/2507.05527/) (2025)
- [Uncertainty Quantification for Evaluating Machine Translation Bias](https://mlsanity.com/paper/2507.18338/) (2025)
- [Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods](https://mlsanity.com/paper/2510.26038/) (2025)
- [Gender Encoding Patterns in Pretrained Language Model Representations](https://mlsanity.com/paper/2503.06734/) (2025)
- [Implicit Design Choices and Their Impact on Emotion Recognition Model Development and Evaluation](https://mlsanity.com/paper/2309.03238/) (2023)
- [FairFlow: Mitigating Dataset Biases through Undecided Learning](https://mlsanity.com/paper/2503.17632/) (2025)
- [Bias Dynamics in BabyLMs: Towards a Compute-Efficient Sandbox for Democratising Pre-Training Debiasing](https://mlsanity.com/paper/2601.09421/) (2026)

## Abstract (arXiv)

Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring models into making unbiased predictions. An underlying assumption behind such methods is that this also leads to the discovery of more robust features in the model's inner representations. We propose a general probing-based framework that allows for post-hoc interpretation of biases in language models, and use an information-theoretic approach to measure the extractability of certain biases from the model's representations. We experiment with several NLU datasets and known biases, and show that, counter-intuitively, the more a language model is pushed towards a debiased regime, the more bias is actually encoded in its inner representations.