# Deep Learning for Bias Detection: From Inception to Deployment

arXiv: https://arxiv.org/abs/2110.15728 · HTML: https://mlsanity.com/paper/2110.15728/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 50 references that are in the map.
- First posted on arXiv 12 Oct 2021.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019)
- [Advances in Pre-Training Distributed Word Representations](https://mlsanity.com/paper/1712.09405/) (2017)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Exploring the Limits of Language Modeling](https://mlsanity.com/paper/1602.02410/) (2016)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://mlsanity.com/paper/1904.04047/) (2019)
- [Automatically Neutralizing Subjective Bias in Text](https://mlsanity.com/paper/1911.09709/) (2019)
- [It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution](https://mlsanity.com/paper/1909.00871/) (2019)
- [Quasi-Recurrent Neural Networks](https://mlsanity.com/paper/1611.01576/) (2016)
- [Multi-Dimensional Gender Bias Classification](https://mlsanity.com/paper/2005.00614/) (2020)
- [Gender-preserving Debiasing for Pre-trained Word Embeddings](https://mlsanity.com/paper/1906.00742/) (2019)
- [Diversity and Inclusion Metrics in Subset Selection](https://mlsanity.com/paper/2002.03256/) (2020)
- [Automatic Detection of Sexist Statements Commonly Used at the Workplace](https://mlsanity.com/paper/2007.04181/) (2020)
- [QutNocturnal@HASOC'19: CNN for Hate Speech and Offensive Content Identification in Hindi Language](https://mlsanity.com/paper/2008.12448/) (2020)
- [Misogynistic Tweet Detection: Modelling CNN with Small Datasets](https://mlsanity.com/paper/2008.12452/) (2020)

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

- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Informed Machine Learning, Centrality, CNN, Relevant Document Detection, Repatriation of Indigenous Human Remains](https://mlsanity.com/paper/2303.14475/) (2023)

## Abstract (arXiv)

To create a more inclusive workplace, enterprises are actively investing in identifying and eliminating unconscious bias (e.g., gender, race, age, disability, elitism and religion) across their various functions. We propose a deep learning model with a transfer learning based language model to learn from manually tagged documents for automatically identifying bias in enterprise content. We first pretrain a deep learning-based language-model using Wikipedia, then fine tune the model with a large unlabelled data set related with various types of enterprise content. Finally, a linear layer followed by softmax layer is added at the end of the language model and the model is trained on a labelled bias dataset consisting of enterprise content. The trained model is thoroughly evaluated on independent datasets to ensure a general application. We present the proposed method and its deployment detail in a real-world application.