Using generative AI tools and LARA to create multimodal language learning resources for L2 Icelandic

Abstract

[EN] We utilize ChatGPT and other generative AI tools in developing illustrated multimodal resources for learning Icelandic as a second language (L2) via reading in the online platform LARA. These are illustrated short stories in Icelandic created using specific prompts including information about learner levels and age groups. We present a methodology for creating engaging stories and a way to evaluate the quality and suitability of text and images generated by AI. Additionally, we assess how 46 adult learners perceived reading a story at A1 and A2 level in LARA, with a positive vocabulary learning effect. We conclude that generating suitable prompts greatly assists with getting the desired output; however, this is restricted to the language one works with. Much human post-editing is still necessary for Icelandic texts to improve their quality in grammar, vocabulary, and cultural aspects, and their suitability for language teaching.