# Evaluating Large Language Models for Hausa and Fongbe Machine Translation: Benchmarks, Failures, and Metric Reliability

arXiv: https://arxiv.org/abs/2606.22269 · HTML: https://mlsanity.com/paper/2606.22269/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 20 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [Are All Languages Created Equal in Multilingual BERT?](https://mlsanity.com/paper/2005.09093/) (2020)
- [CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB](https://mlsanity.com/paper/1911.04944/) (2019)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages](https://mlsanity.com/paper/2010.02353/) (2020)
- [Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning](https://mlsanity.com/paper/2204.06487/) (2022)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information](https://mlsanity.com/paper/2005.02354/) (2020)
- [AFRIDOC-MT: Document-level MT Corpus for African Languages](https://mlsanity.com/paper/2501.06374/) (2025)
- [English2Gbe: A multilingual machine translation model for {Fon/Ewe}Gbe](https://mlsanity.com/paper/2112.11482/) (2021)
- [FFSTC: Fongbe to French Speech Translation Corpus](https://mlsanity.com/paper/2403.05488/) (2024)

## Abstract (arXiv)

We investigate the translation quality of current large language models (LLMs) for English-to-Hausa and English-to-Fongbe - two typologically distinct West African languages from the Afroasiatic and Niger-Congo families respectively - and evaluate whether standard automatic metrics reliably reflect human judgment for these low-resource languages. We evaluate four models (GPT-4o Mini, Claude Sonnet 4, Gemini 2.5 Flash, and Qwen2.5-7B) at progressive scales (500 to 10,000 sentences) using automatic metrics (BLEU, chrF++, TER, COMET, BERTScore) validated against native-speaker judgment. Our results reveal three key findings. First, translation quality varies substantially by language: Hausa achieves acceptable quality (human scores 4.0-4.5/5) while Fongbe achieves poor quality (1.0-2.2/5), with a consistent 3x BLEU gap across all systems. Second, model rankings differ by language - Gemini leads for Fongbe while GPT-4o leads for Hausa by human evaluation - indicating that performance on one low-resource African language does not predict performance on another. Third, metric-human correlation varies dramatically: perfect rank correlation for Fongbe (rho=1.0) but weak correlation for Hausa (rho=0.5), where human evaluators preferred GPT-4o despite all automatic metrics ranking Claude first. We further show that neural metrics like BERTScore exhibit embedding collapse (within-language similarity >0.99) for both languages, limiting their ability to differentiate translation quality. Based on these findings, we recommend multi-metric evaluation for low-resource African languages, with particular caution when interpreting neural metrics. We establish that minimum sample sizes of n=2,500 sentences are required for stable system rankings, as smaller samples produced artifact findings that reversed at scale.