SubmissionNumber#=%=#27 FinalPaperTitle#=%=#JSI and W\"{u}NLP at the DIALECT-COPA Shared Task: In-Context Learning From Just a Few Dialectal Examples Gets You Quite Far ShortPaperTitle#=%=# NumberOfPages#=%=#11 CopyrightSigned#=%=# JobTitle#==# Organization#==# Abstract#==#The paper presents the JSI and W\"{u}NLP systems submitted to the DIALECT-COPA shared task on causal commonsense reasoning in dialectal texts. Jointly, we compare LLM-based zero-shot and few-shot in-context inference (JSI team), and task-specific few-shot fine-tuning, in English and respective standard language, with zero-shot cross-lingual transfer (ZS-XLT) to the test dialects (W\"{u}NLP team). Given the very strong zero-shot and especially few-shot in-context learning (ICL) performance, we further investigate whether task semantics, or language/dialect semantics explain the strong performance, showing that a significant part of the improvement indeed stems from learning the language or dialect semantics from the in-context examples, with only a minor contribution from understanding the nature of the task. The higher importance of the dialect semantics to the task semantics is further shown by the finding that the in-context learning with only a few dialectal instances achieves comparable results to the supervised fine-tuning approach on hundreds of instances in standard language. Author{1}{Firstname}#=%=#Nikola Author{1}{Lastname}#=%=#Ljubešić Author{1}{Username}#=%=#nljubesi Author{1}{Email}#=%=#nikola.ljubesic@ijs.si Author{1}{Affiliation}#=%=#Jožef Stefan Institute Author{2}{Firstname}#=%=#Taja Author{2}{Lastname}#=%=#Kuzman Author{2}{Username}#=%=#tajakuz Author{2}{Email}#=%=#taja.kuzman@ijs.si Author{2}{Affiliation}#=%=#Jožef Stefan Institute Author{3}{Firstname}#=%=#Peter Author{3}{Lastname}#=%=#Rupnik Author{3}{Username}#=%=#boutrosboutrosrupnik Author{3}{Email}#=%=#peter.rupnik@ijs.si Author{3}{Affiliation}#=%=#Jožef Stefan Institute Author{4}{Firstname}#=%=#Ivan Author{4}{Lastname}#=%=#Vulić Author{4}{Username}#=%=#ivulic Author{4}{Email}#=%=#iv250@cam.ac.uk Author{4}{Affiliation}#=%=#University of Cambridge Author{5}{Firstname}#=%=#Fabian David Author{5}{Lastname}#=%=#Schmidt Author{5}{Username}#=%=#fdschmidt93 Author{5}{Email}#=%=#fabian.david.schmidt@gmail.com Author{5}{Affiliation}#=%=#University of Wuerzburg Author{6}{Firstname}#=%=#Goran Author{6}{Lastname}#=%=#Glavaš Author{6}{Username}#=%=#gg42554 Author{6}{Email}#=%=#goran.glavas@uni-wuerzburg.de Author{6}{Affiliation}#=%=#University of Würzburg ========== èéáğö