Scalvini, BarbaraSimonsen, AnnikaDebess, Iben NyholmEinarsson, HafsteinnJohansson, RichardStymne, Sara2025-02-192025-02-192025-03https://hdl.handle.net/10062/107256This study evaluates GPT-4's English-to-Faroese translation capabilities, comparing it with multilingual models on FLORES-200 and Sprotin datasets. We propose a prompt optimization strategy using Semantic Textual Similarity (STS) to improve translation quality. Human evaluation confirms the effectiveness of STS-based few-shot example selection, though automated metrics fail to capture these improvements. Our findings advance LLM applications for low-resource language translation while highlighting the need for better evaluation methods in this context.enAttribution-NonCommercial-NoDerivatives 4.0 Internationalhttps://creativecommons.org/licenses/by-nc-nd/4.0/Article