UrduMMLU: New Benchmark Reveals Gaps in Large Language Models' Urdu Language Understanding
Researchers have created UrduMMLU, a benchmark of over 26,000 Urdu multiple-choice questions across 26 subjects, to evaluate how well large language models understand Urdu—a language spoken by over 230 million people. The benchmark, built from native educational sources rather than translations, reveals significant performance gaps, with most models struggling particularly on Urdu-specific humanities content. The findings highlight the need for more robust multilingual AI evaluation in non-English languages.
Researchers introduced UrduMMLU, a comprehensive benchmark containing 26,431 multiple-choice questions in Urdu across 26 subjects and five domains, sourced from native Urdu educational materials and public examination PDFs. Unlike translation-based benchmarks, UrduMMLU includes both standard academic subjects and Urdu- and region-specific content, with exam-derived questions validated through dual human annotation. Evaluation of 30 large language models showed Gemini-3.5-Flash achieving the highest accuracy at around 90%, while no other model exceeded 85%. Open-source models performed significantly worse, trailing by 8-9 percentage points, and many models lost 25-40 percentage points on Urdu-centered humanities subjects compared to STEM topics. The research demonstrates that current LLMs have uneven knowledge of Urdu, particularly for regionally grounded content, and that few-shot prompting provides only modest improvements.
What's missing
The study does not discuss potential limitations in the benchmark's geographic or demographic representation within Urdu-speaking regions, nor does it address how performance might vary across different Urdu dialects or writing conventions.
What different sources said
- arXiv cs.CLCenter
Phun-Bench: Evaluating LLMs on Phonological Understanding in Chinese
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.