CONF Jiang_EACL2026_2026/IDIAP Analogical Structure, Minimal Contextual Cues and Contrastive Distractors: Input Design for Sample-Efficient Linguistic Rule Induction Jiang, Chunyang Merlo, Paola https://publications.idiap.ch/index.php/publications/showcite/Jiang_ARXIV_2025 Related documents Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) 2026 Association for Computational Linguistics Rabat, Morocco 485--500 979-8-89176-380-7 https://aclanthology.org/2026.eacl-long.22/ URL 10.18653/v1/2026.eacl-long.22 doi Large language models achieve strong performance on many tasks, but their training makes it hard to see which properties of the input support efficient linguistic rule learning.We ask how three cognitively-inspired principles of input design support sample-efficient linguistic rule induction: analogical structure, contrastive learning, and minimal contextual cue. We also ask how their effects compare to those of LLMs on the same controlled tasks.We implement these principles in structured sentence completion tasks that test English verb alternations.Lightweight models trained on hundreds to one-thousand such examples learn the alternation rules with high F1 on these tasks. Ablation studies show that analogical organisation is the main driver of sample efficiency, and contrastive distractors and minimal context help further gains. We also evaluate zero- and few-shot LLMs on the same tasks. In this controlled setting, the lightweight models reach higher F1 with far fewer task-specific data.We treat this contrast as a comparison between learning regimes rather than a general verdict on LLMs.Our results show that careful input organisation supports sample-efficient learning of linguistic rules and reveals distinct learning signatures for trained lightweight models and prompted LLMs. CONF Jiang_ARXIV_2025/IDIAP Analogical Structure, Minimal Contextual Cues and Contrastive Distractors: Input Design for Sample-Efficient Linguistic Rule Induction Jiang, Chunyang Merlo, Paola arXiv cs.CL.2511.10441 2025