# Social Norm Bias: Residual Harms of Fairness-Aware Algorithms

arXiv: https://arxiv.org/abs/2108.11056 · HTML: https://mlsanity.com/paper/2108.11056/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 103 references that are in the map.
- First posted on arXiv 25 Aug 2021.

## Builds on (most cited first, 30 of 39)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [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)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks](https://mlsanity.com/paper/1608.04207/) (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)
- [Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices](https://mlsanity.com/paper/1906.09208/) (2019)
- [Predictive Multiplicity in Classification](https://mlsanity.com/paper/1909.06677/) (2019)
- [Reducing Gender Bias in Abusive Language Detection](https://mlsanity.com/paper/1808.07231/) (2018)
- [Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search](https://mlsanity.com/paper/1905.01989/) (2019)
- [Towards a Critical Race Methodology in Algorithmic Fairness](https://mlsanity.com/paper/1912.03593/) (2019)
- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [Toward Gender-Inclusive Coreference Resolution](https://mlsanity.com/paper/1910.13913/) (2019)
- [Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias](https://mlsanity.com/paper/2010.14534/) (2020)
- [Bias Mitigation Post-processing for Individual and Group Fairness](https://mlsanity.com/paper/1812.06135/) (2018)
- [What's in a Name? Reducing Bias in Bios without Access to Protected Attributes](https://mlsanity.com/paper/1904.05233/) (2019)

## Built on by (most cited first, 6 of 6)

- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations](https://mlsanity.com/paper/2310.11501/) (2023)
- [HumT DumT: Measuring and controlling human-like language in LLMs](https://mlsanity.com/paper/2502.13259/) (2025)
- [Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness](https://mlsanity.com/paper/2310.06161/) (2023)
- [More Data Can Lead Us Astray: Active Data Acquisition in the Presence of Label Bias](https://mlsanity.com/paper/2207.07723/) (2022)
- [VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigation](https://mlsanity.com/paper/2601.00996/) (2026)

## Abstract (arXiv)

Many modern machine learning algorithms mitigate bias by enforcing fairness constraints across coarsely-defined groups related to a sensitive attribute like gender or race. However, these algorithms seldom account for within-group heterogeneity and biases that may disproportionately affect some members of a group. In this work, we characterize Social Norm Bias (SNoB), a subtle but consequential type of algorithmic discrimination that may be exhibited by machine learning models, even when these systems achieve group fairness objectives. We study this issue through the lens of gender bias in occupation classification. We quantify SNoB by measuring how an algorithm's predictions are associated with conformity to inferred gender norms. When predicting if an individual belongs to a male-dominated occupation, this framework reveals that "fair" classifiers still favor biographies written in ways that align with inferred masculine norms. We compare SNoB across algorithmic fairness methods and show that it is frequently a residual bias, and post-processing approaches do not mitigate this type of bias at all.