# Richer Countries and Richer Representations

arXiv: https://arxiv.org/abs/2205.05093 · HTML: https://mlsanity.com/paper/2205.05093/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 10 May 2022.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations](https://mlsanity.com/paper/1808.09121/) (2018)
- [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)
- [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://mlsanity.com/paper/2005.00813/) (2020)
- [Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings](https://mlsanity.com/paper/2003.11515/) (2020)
- [Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English](https://mlsanity.com/paper/1707.00061/) (2017)
- [Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoders](https://mlsanity.com/paper/2005.02590/) (2020)
- [Understanding Undesirable Word Embedding Associations](https://mlsanity.com/paper/1908.06361/) (2019)
- [Towards Understanding Linear Word Analogies](https://mlsanity.com/paper/1810.04882/) (2018)
- ["You are grounded!": Latent Name Artifacts in Pre-trained Language Models](https://mlsanity.com/paper/2004.03012/) (2020)
- [Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models](https://mlsanity.com/paper/2110.00672/) (2021)
- [Utility is in the Eye of the User: A Critique of NLP Leaderboards](https://mlsanity.com/paper/2009.13888/) (2020)

## Built on by (most cited first, 7 of 7)

- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters](https://mlsanity.com/paper/2401.06408/) (2024)
- [Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation](https://mlsanity.com/paper/2402.01705/) (2024)
- [Geographical Erasure in Language Generation](https://mlsanity.com/paper/2310.14777/) (2023)
- [Discovering Differences in the Representation of People using Contextualized Semantic Axes](https://mlsanity.com/paper/2210.12170/) (2022)
- [Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance](https://mlsanity.com/paper/2310.05597/) (2023)
- [Where Do Images Come From? Analyzing Captions to Geographically Profile Datasets](https://mlsanity.com/paper/2602.09775/) (2026)

## Abstract (arXiv)

We examine whether some countries are more richly represented in embedding space than others. We find that countries whose names occur with low frequency in training corpora are more likely to be tokenized into subwords, are less semantically distinct in embedding space, and are less likely to be correctly predicted: e.g., Ghana (the correct answer and in-vocabulary) is not predicted for, "The country producing the most cocoa is [MASK].". Although these performance discrepancies and representational harms are due to frequency, we find that frequency is highly correlated with a country's GDP; thus perpetuating historic power and wealth inequalities. We analyze the effectiveness of mitigation strategies; recommend that researchers report training word frequencies; and recommend future work for the community to define and design representational guarantees.