New Benchmarks Advance Language Model Evaluation for Low-Resource and Specialized Languages
Researchers have introduced SkMTEB, the first large-scale text embedding benchmark for Slovak, covering 31 datasets across 7 task types. The work also produced two open-source Slovak embedding models derived from Multilingual E5 by vocabulary trimming and fine-tuning. The benchmark and models aim to provide a replicable framework for improving NLP infrastructure in other low-resource languages.
A team of researchers has published SkMTEB, the first MTEB-style (Massive Text Embedding Benchmark) evaluation suite tailored to Slovak, a low-resource West Slavic language. The benchmark encompasses 31 datasets spanning 7 task types, representing nearly four times the depth of existing multilingual benchmark coverage for Slovak. An evaluation of 31 embedding models found that large instruction-tuned multilingual models perform best, while Slovak-specific models previously trained for natural language understanding (NLU) tasks transfer poorly to embedding tasks. To fill the practical gap for efficient, locally-deployable solutions, the authors created two models — e5-sk-small (45M parameters) and e5-sk-large (365M parameters) — by applying vocabulary trimming and fine-tuning to existing Multilingual E5 models. Despite parameter reductions of up to 62%, these models achieve competitive performance with proprietary API-based systems and are suitable for semantic search and retrieval-augmented generation (RAG). All benchmark data, models, datasets, and code are released openly, and the paper has been accepted to ACL 2026.
What's missing
It is unclear how performance compares on domain-specific Slovak text (e.g., legal, medical) versus general-domain text, and whether the vocabulary trimming procedure introduces any systematic degradation for rare Slovak morphological forms.
What different sources said
- arXiv cs.CLCenter
LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis
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.