[Paper] Supervision versus Demonstration-Based In-Context Learning for Multiword Expression Classification
Source: arXiv - 2606.07479v1
Overview
Turkish idiomatic light verb constructions (LVCs) are challenging for multiword expression processing because they often share the same surface form as fully literal verb-object combinations while functioning as a single, partially idiomatic predicate. We frame Turkish LVC detection as a binary classification task (literal meaning vs. idiomatic meaning) and evaluate on a manually created controlled set (N=147) with matched negatives: out-of-domain random sentences and in-domain literal controls (NLVC), alongside LVC positives. We compare a supervised Turkish encoder baseline (BERTurk with a classifier head) to three instruction-tuned LLMs from different families under zero-shot, one-shot, and few-shot prompting, and analyze how demonstrations shift error profiles. In zero-shot, LLMs perform well on negatives but show very low LVC recall. One-shot prompting sharply improves LVC detection but can induce strong, model-specific biases, leading models to overpredict or underpredict LVCs. A richer few-shot prompt improves calibration and yields robust overall performance for GPT-OSS-20B and Qwen 2.5-14B. Overall, the results highlight substantial prompt sensitivity in Turkish metalinguistic classification: the supervised baseline remains competitive, while prompted LLMs can match or exceed it on LVCs with carefully constructed demonstrations.
Key Contributions
This paper presents research in the following areas:
- cs.CL
- cs.AI
Methodology
Please refer to the full paper for detailed methodology.
Practical Implications
This research contributes to the advancement of cs.CL.
Authors
- Sercan Karakaş
- Yusuf Şimşek
Paper Information
- arXiv ID: 2606.07479v1
- Categories: cs.CL, cs.AI
- Published: June 5, 2026
- PDF: Download PDF