Study Compares Supervised Learning and In-Context Prompting for Turkish Idiomatic Expression Classification
Researchers evaluated supervised machine learning and large language models on detecting Turkish light verb constructions (idiomatic expressions that resemble literal verb-object combinations). The study found that while LLMs perform well with zero-shot prompting on negative examples, they require carefully constructed demonstrations to reliably identify idiomatic expressions. The findings suggest that prompt design significantly affects model performance on linguistic classification tasks, with implications for how LLMs are applied to language-specific NLP challenges.
A new study on arXiv compares supervised learning and demonstration-based in-context learning for classifying Turkish light verb constructions (LVCs)—idiomatic expressions that are difficult to identify because they share surface forms with literal verb-object combinations. Researchers created a controlled test set of 147 examples with matched negative cases (random out-of-domain sentences and in-domain literal controls) and compared a supervised Turkish BERT model against three instruction-tuned large language models under zero-shot, one-shot, and few-shot prompting conditions. Results showed that LLMs excel at rejecting negative examples in zero-shot settings but struggle to identify actual LVCs without demonstrations. Adding a single example (one-shot) dramatically improved LVC detection but introduced model-specific biases causing over- or underprediction. A richer few-shot prompt improved calibration, with GPT-OSS-20B and Qwen 2.5-14B achieving competitive or superior performance compared to the supervised baseline. The study highlights substantial sensitivity to prompt construction in Turkish metalinguistic classification tasks.
What's missing
The study does not discuss potential applications or downstream impacts of improved LVC detection for Turkish NLP systems, nor does it address whether findings generalize to other morphologically rich or agglutinative languages with similar idiomatic expression challenges.
What different sources said
- arXiv cs.CLCenter
Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification
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.