New Benchmark Reveals LLM Weakness in Distinguishing Similar Arabic-Hebrew Words
Researchers have introduced SemCog Bench, a 1,858-word-pair benchmark testing large language models on Arabic–Hebrew cognates, false friends, and loanwords. While LLMs perform well on true cognates, accuracy drops sharply on false friends and loanwords, revealing over-reliance on surface-form similarity. The findings highlight a fundamental gap in cross-lingual semantic reasoning that current models have yet to overcome.
A team of researchers has released SemCog Bench, a curated benchmark of 1,858 Arabic–Hebrew word pairs annotated at the sentence level for cognate identification and semantic disambiguation. The benchmark evaluates both open-source and commercial LLMs across four input representations: raw, diacritized, Romanized, and phonetic. Results show that models achieve high accuracy on true cognates but fail significantly on false friends and loanwords, suggesting they rely heavily on surface-form similarity rather than deeper semantic understanding. Sentence-level context provided only modest performance improvements, indicating that contextual cues alone are insufficient to resolve misleading form-based signals. The study covers Arabic and Hebrew as closely related Semitic languages that share substantial lexical overlap, making cross-lingual disambiguation particularly challenging. The authors argue these findings reveal a fundamental limitation in how current LLMs handle cross-lingual form–meaning conflicts. Both the code and dataset have been made publicly available to support further research.
What's missing
The benchmark currently covers only one language pair; it is unclear whether the observed limitations extend to other Semitic or morphologically rich language pairs. The study also does not address whether fine-tuning on cognate-specific data could close the identified performance gap.
What different sources said
- arXiv cs.CLCenter
When Similar Means Different: Evaluating LLMs on Arabic--Hebrew Cognates
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.