# SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context

arXiv: https://arxiv.org/abs/2602.22404 · HTML: https://mlsanity.com/paper/2602.22404/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 20 of 20)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets](https://mlsanity.com/paper/2103.12028/) (2021)
- [On Measuring and Mitigating Biased Inferences of Word Embeddings](https://mlsanity.com/paper/1908.09369/) (2019)
- [A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation](https://mlsanity.com/paper/2205.02022/) (2022)
- [SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models](https://mlsanity.com/paper/2305.11840/) (2023)
- [Towards Afrocentric NLP for African Languages: Where We Are and Where We Can Go](https://mlsanity.com/paper/2203.08351/) (2022)
- [Handling and Presenting Harmful Text in NLP Research](https://mlsanity.com/paper/2204.14256/) (2022)
- [AfroBench: How Good are Large Language Models on African Languages?](https://mlsanity.com/paper/2311.07978/) (2023)
- [Data Governance in the Age of Large-Scale Data-Driven Language Technology](https://mlsanity.com/paper/2206.03216/) (2022)
- [Building Socio-culturally Inclusive Stereotype Resources with Community Engagement](https://mlsanity.com/paper/2307.10514/) (2023)
- [SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypes](https://mlsanity.com/paper/2403.05696/) (2024)
- [AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages](https://mlsanity.com/paper/2501.08284/) (2025)
- [Are Generative Language Models Multicultural? A Study on Hausa Culture and Emotions using ChatGPT](https://mlsanity.com/paper/2406.19504/) (2024)
- [Socially Responsible Data for Large Multilingual Language Models](https://mlsanity.com/paper/2409.05247/) (2024)
- [A Comprehensive Framework to Operationalize Social Stereotypes for Responsible AI Evaluations](https://mlsanity.com/paper/2501.02074/) (2025)
- [HESEIA: A community-based dataset for evaluating social biases in large language models, co-designed in real school settings in Latin America](https://mlsanity.com/paper/2505.24712/) (2025)
- [Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce](https://mlsanity.com/paper/2410.12691/) (2024)

## Built on by (most cited first, 1 of 1)

- [Toward Culturally Grounded Natural Language Processing](https://mlsanity.com/paper/2603.26013/) (2026)

## Abstract (arXiv)

Stereotype repositories are critical to assess generative AI model safety, but currently lack adequate global coverage. It is imperative to prioritize targeted expansion, strategically addressing existing deficits, over merely increasing data volume. This work introduces a multilingual stereotype resource covering four sub-Saharan African countries that are severely underrepresented in NLP resources: Ghana, Kenya, Nigeria, and South Africa. By utilizing socioculturally-situated, community-engaged methods, including telephonic surveys moderated in native languages, we establish a reproducible methodology that is sensitive to the region's complex linguistic diversity and traditional orality. By deliberately balancing the sample across diverse ethnic and demographic backgrounds, we ensure broad coverage, resulting in a dataset of 3,534 stereotypes in English and 3,206 stereotypes across 15 native languages.