# Towards Model as a Library: Offline, Community-Sourced AI for Low-Resource African Languages

arXiv: https://arxiv.org/abs/2609.38574 · HTML: https://mlsanity.com/paper/2609.38574/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 12 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [MLPerf Tiny Benchmark](https://mlsanity.com/paper/2106.07597/) (2021)
- [Edge Impulse: An MLOps Platform for Tiny Machine Learning](https://mlsanity.com/paper/2212.03332/) (2022)
- [Few-Shot Keyword Spotting With Prototypical Networks](https://mlsanity.com/paper/2007.14463/) (2020)
- [InkubaLM: A small language model for low-resource African languages](https://mlsanity.com/paper/2408.17024/) (2024)
- [Does Generative AI speak Nigerian-Pidgin?: Issues about Representativeness and Bias for Multilingualism in LLMs](https://mlsanity.com/paper/2404.19442/) (2024)
- [Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings](https://mlsanity.com/paper/2605.16993/) (2026)

## Abstract (arXiv)

Large language models are frequently proposed as a route to AI-powered services for African communities, but they are least reliable exactly where the need is greatest: all African languages remain low-resource by any standard measure, and models trained on scraped, standardised text systematically misrepresent the dialectal and regional variation of how people actually speak. We introduce Model as a Library (MaaL), a software architecture that packages small, community-enrolled speech models as versioned on-device dependencies, enabling offline structured data collection that cannot generatively hallucinate, for populations that current language models serve worst. Rather than relying on web-scraped corpora, MaaL's vocabulary is enrolled directly from a small number of example recordings by the speakers themselves, at the point of deployment. We describe the architecture and its central mechanism - keyword spotting that turns a closed-vocabulary text form into a voice form, filled and submitted entirely on-device - and propose transpiling the closed-vocabulary elements already present in widely-deployed digital form tools into MaaL schemas, a low-friction path to voice-first, offline data collection for the low-literacy populations these tools already reach. This is a position and system-design paper: we describe the concept, the mechanism, and an analytical feasibility case, and identify what a working implementation still requires.