# A methodology to characterize bias and harmful stereotypes in natural language processing in Latin America

arXiv: https://arxiv.org/abs/2207.06591 · HTML: https://mlsanity.com/paper/2207.06591/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 14 Jul 2022.

## Builds on (most cited first, 22 of 22)

- [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)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [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)
- [The What-If Tool: Interactive Probing of Machine Learning Models](https://mlsanity.com/paper/1907.04135/) (2019)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- [Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation](https://mlsanity.com/paper/1911.03842/) (2019)
- [The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models](https://mlsanity.com/paper/2008.05122/) (2020)
- [Understanding the Origins of Bias in Word Embeddings](https://mlsanity.com/paper/1810.03611/) (2018)
- [A Survey of Race, Racism, and Anti-Racism in NLP](https://mlsanity.com/paper/2106.11410/) (2021)
- [Examining Gender Bias in Languages with Grammatical Gender](https://mlsanity.com/paper/1909.02224/) (2019)
- [Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors](https://mlsanity.com/paper/1904.11783/) (2019)
- [Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor](https://mlsanity.com/paper/1905.09866/) (2019)
- [Mitigating Gender Bias Amplification in Distribution by Posterior Regularization](https://mlsanity.com/paper/2005.06251/) (2020)
- [Dictionary-based Debiasing of Pre-trained Word Embeddings](https://mlsanity.com/paper/2101.09525/) (2021)
- [Debiasing Embeddings for Reduced Gender Bias in Text Classification](https://mlsanity.com/paper/1908.02810/) (2019)
- [How does Grammatical Gender Affect Noun Representations in Gender-Marking Languages?](https://mlsanity.com/paper/1910.14161/) (2019)
- [WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings](https://mlsanity.com/paper/2103.03598/) (2021)
- [Redefining Context Windows for Word Embedding Models: An Experimental Study](https://mlsanity.com/paper/1704.05781/) (2017)
- [VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations](https://mlsanity.com/paper/2104.02797/) (2021)

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

- [Post-hoc Study of Climate Microtargeting on Social Media Ads with LLMs: Thematic Insights and Fairness Evaluation](https://mlsanity.com/paper/2410.05401/) (2024)
- [Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration](https://mlsanity.com/paper/2607.07895/) (2026)

## Abstract (arXiv)

Automated decision-making systems, especially those based on natural language processing, are pervasive in our lives. They are not only behind the internet search engines we use daily, but also take more critical roles: selecting candidates for a job, determining suspects of a crime, diagnosing autism and more. Such automated systems make errors, which may be harmful in many ways, be it because of the severity of the consequences (as in health issues) or because of the sheer number of people they affect. When errors made by an automated system affect a population more than others, we call the system textitbiased. Most modern natural language technologies are based on artifacts obtained from enormous volumes of text using machine learning, namely language models and word embeddings. Since they are created by applying subsymbolic machine learning, mostly artificial neural networks, they are opaque and practically uninterpretable by direct inspection, thus making it very difficult to audit them. In this paper, we present a methodology that spells out how social scientists, domain experts, and machine learning experts can collaboratively explore biases and harmful stereotypes in word embeddings and large language models. Our methodology is based on the following principles: * focus on the linguistic manifestations of discrimination on word embeddings and language models, not on the mathematical properties of the models * reduce the technical barrier for discrimination experts%, be it social scientists, domain experts or other * characterize through a qualitative exploratory process in addition to a metric-based approach * address mitigation as part of the training process, not as an afterthought