Advancing Uto-Aztecan Language Technologies: A Case Study on the Endangered Comanche Language

TL;DR

This paper explores how minimal-cost, community-informed NLP techniques can support the preservation of the endangered Comanche language, demonstrating promising results with large language models in low-resource settings.

Contribution

It introduces the first computational study of Comanche, including a curated dataset, data generation pipeline, and evaluation of GPT models for language identification.

Findings

Few-shot prompting greatly improves LLM performance on Comanche

LLMs struggle with zero-shot language identification in low-resource settings

Targeted NLP approaches can aid endangered language preservation

Abstract

The digital exclusion of endangered languages remains a critical challenge in NLP, limiting both linguistic research and revitalization efforts. This study introduces the first computational investigation of Comanche, an Uto-Aztecan language on the verge of extinction, demonstrating how minimal-cost, community-informed NLP interventions can support language preservation. We present a manually curated dataset of 412 phrases, a synthetic data generation pipeline, and an empirical evaluation of GPT-4o and GPT-4o-mini for language identification. Our experiments reveal that while LLMs struggle with Comanche in zero-shot settings, few-shot prompting significantly improves performance, achieving near-perfect accuracy with just five examples. Our findings highlight the potential of targeted NLP methodologies in low-resource contexts and emphasize that visibility is the first step toward inclusion. By establishing a foundation for Comanche in NLP, we advocate for computational approaches that prioritize accessibility, cultural sensitivity, and community engagement.