# Geographic and Geopolitical Biases of Language Models

arXiv: https://arxiv.org/abs/2212.10408 · HTML: https://mlsanity.com/paper/2212.10408/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [mGPT: Few-Shot Learners Go Multilingual](https://mlsanity.com/paper/2204.07580/) (2022)
- [Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset](https://mlsanity.com/paper/2205.12522/) (2022)
- [Mitigating Language-Dependent Ethnic Bias in BERT](https://mlsanity.com/paper/2109.05704/) (2021)
- [Towards Zero-Label Language Learning](https://mlsanity.com/paper/2109.09193/) (2021)
- [PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks](https://mlsanity.com/paper/2202.12499/) (2022)
- [Detecting Cross-Geographic Biases in Toxicity Modeling on Social Media](https://mlsanity.com/paper/2104.06999/) (2021)
- [GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models](https://mlsanity.com/paper/2205.12247/) (2022)
- [Dataset Geography: Mapping Language Data to Language Users](https://mlsanity.com/paper/2112.03497/) (2021)
- [Using Natural Sentences for Understanding Biases in Language Models](https://mlsanity.com/paper/2205.06303/) (2022)
- [Probing as Quantifying Inductive Bias](https://mlsanity.com/paper/2110.08388/) (2021)

## Built on by (most cited first, 29 of 29)

- [Understanding and Mitigating Language Confusion in LLMs](https://mlsanity.com/paper/2406.20052/) (2024)
- [LLMmap: Fingerprinting For Large Language Models](https://mlsanity.com/paper/2407.15847/) (2024)
- [This Land is {Your, My} Land: Evaluating Geopolitical Biases in Language Models](https://mlsanity.com/paper/2305.14610/) (2023)
- [TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning](https://mlsanity.com/paper/2406.15658/) (2024)
- [Are Large Language Models Temporally Grounded?](https://mlsanity.com/paper/2311.08398/) (2023)
- [BiasEdit: Debiasing Stereotyped Language Models via Model Editing](https://mlsanity.com/paper/2503.08588/) (2025)
- [On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications](https://mlsanity.com/paper/2312.17016/) (2023)
- [What Do Language Models Hear? Probing for Auditory Representations in Language Models](https://mlsanity.com/paper/2402.16998/) (2024)
- [Monotonic Representation of Numeric Properties in Language Models](https://mlsanity.com/paper/2403.10381/) (2024)
- [On the Scaling Laws of Geographical Representation in Language Models](https://mlsanity.com/paper/2402.19406/) (2024)
- [Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions](https://mlsanity.com/paper/2502.18470/) (2025)
- [Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models](https://mlsanity.com/paper/2502.15639/) (2025)
- [Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities](https://mlsanity.com/paper/2310.19626/) (2023)
- [OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence](https://mlsanity.com/paper/2503.16326/) (2025)
- [Evaluation of Geographical Distortions in Language Models](https://mlsanity.com/paper/2404.17401/) (2024)
- [Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models](https://mlsanity.com/paper/2410.22517/) (2024)
- [Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI](https://mlsanity.com/paper/2508.05432/) (2025)
- [In Agents We Trust, but Who Do Agents Trust? Latent Source Preferences Steer LLM Generations](https://mlsanity.com/paper/2602.15456/) (2026)
- [FLUKE: A Linguistically-Driven and Task-Agnostic Framework for Robustness Evaluation](https://mlsanity.com/paper/2504.17311/) (2025)
- [GeoBS: Information-Theoretic Quantification of Geographic Bias in AI Models](https://mlsanity.com/paper/2509.23482/) (2025)
- [Regional Bias in Large Language Models](https://mlsanity.com/paper/2601.16349/) (2026)
- [ExpertLens: Activation steering features are highly interpretable](https://mlsanity.com/paper/2502.15090/) (2025)
- [Improving Social Determinants of Health Documentation in French EHRs Using Large Language Models](https://mlsanity.com/paper/2507.03433/) (2025)
- [Coordinates from Context: Using LLMs to Ground Complex Location References](https://mlsanity.com/paper/2510.08741/) (2025)
- [IndRegBias: A Dataset for Studying Indian Regional Biases in English and Code-Mixed Social Media Comments](https://mlsanity.com/paper/2601.06477/) (2026)
- [Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration](https://mlsanity.com/paper/2606.21595/) (2026)
- [Evaluating Regional Bias in LLMs From Abstract Stereotype to Concrete Social Decision-Making](https://mlsanity.com/paper/2607.27022/) (2026)
- [Mapping the City Through the Lens of Language Models](https://mlsanity.com/paper/2608.02971/) (2026)
- [Wiktionary as a Crowdsourced Lexicon for English Dialects](https://mlsanity.com/paper/2608.15641/) (2026)

## Abstract (arXiv)

Pretrained language models (PLMs) often fail to fairly represent target users from certain world regions because of the under-representation of those regions in training datasets. With recent PLMs trained on enormous data sources, quantifying their potential biases is difficult, due to their black-box nature and the sheer scale of the data sources. In this work, we devise an approach to study the geographic bias (and knowledge) present in PLMs, proposing a Geographic-Representation Probing Framework adopting a self-conditioning method coupled with entity-country mappings. Our findings suggest PLMs' representations map surprisingly well to the physical world in terms of country-to-country associations, but this knowledge is unequally shared across languages. Last, we explain how large PLMs despite exhibiting notions of geographical proximity, over-amplify geopolitical favouritism at inference time.