Recent advancements in large language model (LLM) performance on medical multiplechoice question (MCQ) benchmarks have stimulated interest from healthcare providers and patients globally. Particularly in low-andmiddle-income countries (LMICs) facing acute physician shortages and lack of specialists, LLMs offer a potentially scalable pathway to enhance healthcare access and reduce costs. However, their effectiveness in the Global South, especially across the African continent, remains to be established. In this work, we introduce AfriMed-QA , the first largescale Pan-African English multi-specialty medical Question-Answering (QA) dataset, 15,000 questions (open and closed-ended) sourced from over 60 medical schools across 16 countries, covering 32 medical specialties. We further evaluate 30 LLMs across multiple axes including correctness and demographic bias. Our findings show significant performance variation across specialties and geographies, MCQ performance clearly lags USMLE (MedQA). We find that biomedical LLMs underperform general models and smaller edge-friendly LLMs struggle to achieve a passing score. Interestingly, human evaluations show a consistent consumer preference for LLM answers and explanations when compared with clinician answers.

Translating cultural content poses challenges for machine translation systems due to the differences in conceptualizations between cultures, where language alone may fail to convey sufficient context to capture region-specific meanings. In this work, we investigate whether images can act as cultural context in multimodal translation. We introduce CaMMT, a human-curated benchmark of over 5,800 triples of images along with parallel captions in English and regional languages. Using this dataset, we evaluate five Vision Language Models (VLMs) in text-only and text+image settings. Through automatic and human evaluations, we find that visual context generally improves translation quality, especially in handling Culturally-Specific Items (CSIs), disambiguation, and correct gender marking. By releasing CaMMT, our objective is to support broader efforts to build and evaluate multimodal translation systems that are better aligned with cultural nuance and regional variations.

Speech technologies are transforming interactions across various sectors, from healthcare to call centers and robots, yet their performance on African-accented conversations remains underexplored. We introduce Afrispeech-Dialog, a benchmark dataset of 50 simulated medical and non-medical African-accented English conversations, designed to evaluate automatic speech recognition (ASR) and related technologies. We assess state-of-the-art (SOTA) speaker diarization and ASR systems on long-form, accented speech, comparing their performance with native accents and discover a 10%+ performance degradation. Additionally, we explore medical conversation summarization capabilities of large language models (LLMs) to demonstrate the impact of ASR errors on downstream medical summaries, providing insights into the challenges and opportunities for speech technologies in the Global South. Our work highlights the need for more inclusive datasets to advance conversational AI in low-resource settings.

This paper evaluates the language understanding capabilities of various large language models (LLMs) through an analysis of 112 translated and human-edited questions from the Multitask Language Understanding (MMLU) dataset, focusing specifically on two underrepresented languages: Latvian and Giriama. The study compares the performance of six state-of-the-art (SOTA) models, with OpenAI’s o1-preview model demonstrating superior performance across all languages, significantly outperforming non-proprietary models in Latvian and all other models in Giriama. Human editing of automated translations from English to Latvian yielded only a small, statistically insignificant improvement in performance estimates, suggesting that machine-translated benchmarks may be sufficient for comparing model performance in languages with established digital resources like Latvian. However, automated translation to Giriama proved infeasible, and model performance in Giriama remained poor, highlighting the persistent challenges LLMs face with low-resource languages. These findings underscore the need for more comprehensive datasets and improved machine translation capabilities for underrepresented languages, while emphasizing the importance of localized benchmarks and human evaluation in addressing cultural and contextual limitations in AI models.

A majority of language technologies are tailored for a small number of high-resource languages, while relatively many low-resource languages are neglected. One such group, Creole languages, have long been marginalized in academic study, though their speakers could benefit from machine translation (MT). These languages are predominantly used in much of Latin America, Africa and the Caribbean. We present the largest cumulative dataset to date for Creole language MT, including 14.5M unique Creole sentences with parallel translations—11.6M of which we release publicly, and the largest bitexts gathered to date for 41 languages—the first ever for 21. In addition, we provide MT models supporting all 41 Creole languages in 172 translation directions. Given our diverse dataset, we produce a model for Creole language MT exposed to more genre diversity then ever before, which outperforms a genre-specific Creole MT model on its own benchmark for 23 of 34 translation directions.

Despite the recent progress on scaling multilingual machine translation (MT) to several under-resourced African languages, accurately measuring this progress remains challenging, since evaluation is often performed on n-gram matching metrics such as BLEU, which typically show a weaker correlation with human judgments. Learned metrics such as COMET have higher correlation; however, the lack of evaluation data with human ratings for under-resourced languages, complexity of annotation guidelines like Multidimensional Quality Metrics (MQM), and limited language coverage of multilingual encoders have hampered their applicability to African languages. In this paper, we address these challenges by creating high-quality human evaluation data with simplified MQM guidelines for error detection and direct assessment (DA) scoring for 13 typologically diverse African languages. Furthermore, we develop AfriCOMET: COMET evaluation metrics for African languages by leveraging DA data from well-resourced languages and an African-centric multilingual encoder (AfroXLM-R) to create the state-of-the-art MT evaluation metrics for African languages with respect to Spearman-rank correlation with human judgments (0.441).

Social media has become a crucial open-access platform enabling individuals to freely express opinions and share experiences. These platforms contain user-generated content facilitating instantaneous communication and feedback. However, leveraging low-resource language data from Twitter can be challenging due to the scarcity and poor quality of content with significant variations in language use, such as slang and code-switching. Automatically identifying tweets in low-resource languages can also be challenging because Twitter primarily supports high-resource languages; low-resource languages often lack robust linguistic and contextual support. This paper analyzes Kenyan code-switched data from Twitter using four transformer-based pretrained models for sentiment and emotion classification tasks using supervised and semi-supervised methods. We detail the methodology behind data collection, the annotation procedure, and the challenges encountered during the data curation phase. Our results show that XLM-R outperforms other models; for sentiment analysis, XLM-R supervised model achieves the highest accuracy (69.2%) and F1 score (66.1%), XLM-R semi-supervised (67.2% accuracy, 64.1% F1 score). In emotion analysis, DistilBERT supervised leads in accuracy (59.8%) and F1 score (31%), mBERT semi-supervised (accuracy (59% and F1 score 26.5%). AfriBERTa models show the lowest accuracy and F1 scores. This indicates that the semi-supervised method’s performance is constrained by the small labeled dataset.