# Measuring Normative and Descriptive Biases in Language Models Using Census Data

arXiv: https://arxiv.org/abs/2304.05764 · HTML: https://mlsanity.com/paper/2304.05764/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 12 Apr 2023.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [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)
- [CamemBERT: a Tasty French Language Model](https://mlsanity.com/paper/1911.03894/) (2019)
- [Assessing Gender Bias in Machine Translation -- A Case Study with Google Translate](https://mlsanity.com/paper/1809.02208/) (2018)
- [On Measuring Gender Bias in Translation of Gender-neutral Pronouns](https://mlsanity.com/paper/1905.11684/) (2019)
- [BARThez: a Skilled Pretrained French Sequence-to-Sequence Model](https://mlsanity.com/paper/2010.12321/) (2020)
- [Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model](https://mlsanity.com/paper/2104.09617/) (2021)
- [Large-Scale Contextualised Language Modelling for Norwegian](https://mlsanity.com/paper/2104.06546/) (2021)
- [Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements](https://mlsanity.com/paper/2205.11374/) (2022)
- [Good Secretaries, Bad Truck Drivers? Occupational Gender Stereotypes in Sentiment Analysis](https://mlsanity.com/paper/1906.10256/) (2019)
- [Addressing Exposure Bias With Document Minimum Risk Training: Cambridge at the WMT20 Biomedical Translation Task](https://mlsanity.com/paper/2010.05333/) (2020)
- [Measuring Harmful Representations in Scandinavian Language Models](https://mlsanity.com/paper/2211.11678/) (2022)

## Built on by (most cited first, 3 of 3)

- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [NorBench -- A Benchmark for Norwegian Language Models](https://mlsanity.com/paper/2305.03880/) (2023)
- [StereoMap: Quantifying the Awareness of Human-like Stereotypes in Large Language Models](https://mlsanity.com/paper/2310.13673/) (2023)

## Abstract (arXiv)

We investigate in this paper how distributions of occupations with respect to gender is reflected in pre-trained language models. Such distributions are not always aligned to normative ideals, nor do they necessarily reflect a descriptive assessment of reality. In this paper, we introduce an approach for measuring to what degree pre-trained language models are aligned to normative and descriptive occupational distributions. To this end, we use official demographic information about gender--occupation distributions provided by the national statistics agencies of France, Norway, United Kingdom, and the United States. We manually generate template-based sentences combining gendered pronouns and nouns with occupations, and subsequently probe a selection of ten language models covering the English, French, and Norwegian languages. The scoring system we introduce in this work is language independent, and can be used on any combination of template-based sentences, occupations, and languages. The approach could also be extended to other dimensions of national census data and other demographic variables.