# Debiasing Gender Bias in Information Retrieval Models

arXiv: https://arxiv.org/abs/2208.01755 · HTML: https://mlsanity.com/paper/2208.01755/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 2 Aug 2022.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [Learning Gender-Neutral Word Embeddings](https://mlsanity.com/paper/1809.01496/) (2018)
- [Attenuating Bias in Word Vectors](https://mlsanity.com/paper/1901.07656/) (2019)
- [Investigating Gender Bias in BERT](https://mlsanity.com/paper/2009.05021/) (2020)
- [Do Neural Ranking Models Intensify Gender Bias?](https://mlsanity.com/paper/2005.00372/) (2020)
- [Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding](https://mlsanity.com/paper/1911.06156/) (2019)
- [Grep-BiasIR: A Dataset for Investigating Gender Representation-Bias in Information Retrieval Results](https://mlsanity.com/paper/2201.07754/) (2022)
- [Learning Compressed Sentence Representations for On-Device Text Processing](https://mlsanity.com/paper/1906.08340/) (2019)
- [How do lexical semantics affect translation? An empirical study](https://mlsanity.com/paper/2201.00075/) (2021)

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

- [The Pursuit of Fairness in Artificial Intelligence Models: A Survey](https://mlsanity.com/paper/2403.17333/) (2024)
- [EALM: Introducing Multidimensional Ethical Alignment in Conversational Information Retrieval](https://mlsanity.com/paper/2310.00970/) (2023)

## Abstract (arXiv)

Biases in culture, gender, ethnicity, etc. have existed for decades and have affected many areas of human social interaction. These biases have been shown to impact machine learning (ML) models, and for natural language processing (NLP), this can have severe consequences for downstream tasks. Mitigating gender bias in information retrieval (IR) is important to avoid propagating stereotypes. In this work, we employ a dataset consisting of two components: (1) relevance of a document to a query and (2) "gender" of a document, in which pronouns are replaced by male, female, and neutral conjugations. We definitively show that pre-trained models for IR do not perform well in zero-shot retrieval tasks when full fine-tuning of a large pre-trained BERT encoder is performed and that lightweight fine-tuning performed with adapter networks improves zero-shot retrieval performance almost by 20% over baseline. We also illustrate that pre-trained models have gender biases that result in retrieved articles tending to be more often male than female. We overcome this by introducing a debiasing technique that penalizes the model when it prefers males over females, resulting in an effective model that retrieves articles in a balanced fashion across genders.