# Controlling Gender Bias in Retrieval via a Backpack Architecture

arXiv: https://arxiv.org/abs/2511.00875 · HTML: https://mlsanity.com/paper/2511.00875/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 2 Nov 2025.

## Builds on (most cited first, 18 of 18)

- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses](https://mlsanity.com/paper/2210.10634/) (2022)
- [FA*IR: A Fair Top-k Ranking Algorithm](https://mlsanity.com/paper/1706.06368/) (2017)
- [End-to-End Neural Ad-hoc Ranking with Kernel Pooling](https://mlsanity.com/paper/1706.06613/) (2017)
- [Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations](https://mlsanity.com/paper/2102.10073/) (2021)
- [Text Matching as Image Recognition](https://mlsanity.com/paper/1602.06359/) (2016)
- [Designing Fair Ranking Schemes](https://mlsanity.com/paper/1712.09752/) (2017)
- [Fairness in Ranking: A Survey](https://mlsanity.com/paper/2103.14000/) (2021)
- [Do Neural Ranking Models Intensify Gender Bias?](https://mlsanity.com/paper/2005.00372/) (2020)
- [PACRR: A Position-Aware Neural IR Model for Relevance Matching](https://mlsanity.com/paper/1704.03940/) (2017)
- [Gender Stereotype Reinforcement: Measuring the Gender Bias Conveyed by Ranking Algorithms](https://mlsanity.com/paper/2009.01334/) (2020)

## Abstract (arXiv)

The presence of social biases in large language models (LLMs) has become a significant concern in AI research. These biases, often embedded in training data, can perpetuate harmful stereotypes and distort decision-making processes. When LLMs are integrated into ranking systems, they can propagate these biases, leading to unfair outcomes in critical applications such as search engines and recommendation systems. Backpack Language Models, unlike traditional transformer-based models that treat text sequences as monolithic structures, generate outputs as weighted combinations of non-contextual, learned word aspects, also known as senses. Leveraging this architecture, we propose a framework for debiasing ranking tasks. Our experimental results show that this framework effectively mitigates gender bias in text retrieval and ranking with minimal degradation in performance.