Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Left Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models

Abdul-Salem Beibitkhan

Abstract

We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning, technical, and culturally grounded categories, we evaluate 2,000 responses on accuracy, fluency, and completeness. We find a consistent performance gap of 13.8-16.7 percentage points between English and low-resource language conditions, with models maintaining surface-level fluency while producing significantly less accurate content. Cross-lingual transfer-prompting models to reason in English before translating back-yields selective gains for bilingual architectures (+2.2pp to +4.3pp) but provides no benefit to English-dominant models. Our results demonstrate that current LLMs systematically underserve low-resource language communities, and that effective mitigation strategies are architecture-dependent rather than universal.

Left Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models

Abstract

We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning, technical, and culturally grounded categories, we evaluate 2,000 responses on accuracy, fluency, and completeness. We find a consistent performance gap of 13.8-16.7 percentage points between English and low-resource language conditions, with models maintaining surface-level fluency while producing significantly less accurate content. Cross-lingual transfer-prompting models to reason in English before translating back-yields selective gains for bilingual architectures (+2.2pp to +4.3pp) but provides no benefit to English-dominant models. Our results demonstrate that current LLMs systematically underserve low-resource language communities, and that effective mitigation strategies are architecture-dependent rather than universal.
Paper Structure (12 sections, 1 figure, 2 tables)

This paper contains 12 sections, 1 figure, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Benchmark.
  4. Models.
  5. Conditions.
  6. Evaluation.
  7. Results
  8. Discussion
  9. The Fluency Illusion.
  10. CLT as Selective Scaffolding.
  11. Multilingual in Name Only.
  12. Conclusion

Figures (1)

  • Figure 1: Mean score vs. mean response time by model category and condition. The Multilingual C3 point (191.9s, 20.0%) is off-scale and annotated.