# Applying Intrinsic Debiasing on Downstream Tasks: Challenges and Considerations for Machine Translation

arXiv: https://arxiv.org/abs/2406.00787 · HTML: https://mlsanity.com/paper/2406.00787/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 2 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [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)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [Adversarial Removal of Demographic Attributes from Text Data](https://mlsanity.com/paper/1808.06640/) (2018)
- [Intrinsic Bias Metrics Do Not Correlate with Application Bias](https://mlsanity.com/paper/2012.15859/) (2020)
- [Debiasing Pre-trained Contextualised Embeddings](https://mlsanity.com/paper/2101.09523/) (2021)
- [On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations](https://mlsanity.com/paper/2203.13928/) (2022)
- [Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques](https://mlsanity.com/paper/1901.03116/) (2019)
- [Attenuating Bias in Word Vectors](https://mlsanity.com/paper/1901.07656/) (2019)
- [Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender](https://mlsanity.com/paper/2202.11923/) (2022)
- [OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings](https://mlsanity.com/paper/2007.00049/) (2020)
- [Contrastive Learning for Fair Representations](https://mlsanity.com/paper/2109.10645/) (2021)
- [Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information](https://mlsanity.com/paper/2203.07893/) (2022)
- [Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation](https://mlsanity.com/paper/2309.12491/) (2023)
- [Evaluating and Improving the Coreference Capabilities of Machine Translation Models](https://mlsanity.com/paper/2302.08464/) (2023)

## Built on by (most cited first, 2 of 2)

- [Uncertainty Quantification for Evaluating Machine Translation Bias](https://mlsanity.com/paper/2507.18338/) (2025)
- [FairNet: Dynamic Fairness Correction without Performance Loss via Contrastive Conditional LoRA](https://mlsanity.com/paper/2510.19421/) (2025)

## Abstract (arXiv)

Most works on gender bias focus on intrinsic bias -- removing traces of information about a protected group from the model's internal representation. However, these works are often disconnected from the impact of such debiasing on downstream applications, which is the main motivation for debiasing in the first place. In this work, we systematically test how methods for intrinsic debiasing affect neural machine translation models, by measuring the extrinsic bias of such systems under different design choices. We highlight three challenges and mismatches between the debiasing techniques and their end-goal usage, including the choice of embeddings to debias, the mismatch between words and sub-word tokens debiasing, and the effect on different target languages. We find that these considerations have a significant impact on downstream performance and the success of debiasing.