Various aspects of the Elicited Imitation Test (EIT), a sentence repetition task for language assessment, can be automated, for example in terms of test administration or automatic scoring. It is potentially also possible to generate test items with Large Language Models (LLMs). This study investigates the potential of GPT-4o for item creation in the context of EIT, creating a parallel form to two popular and validated tests. We analysed the tests in terms of their linguistic and psychometric properties. While the items created by the LLM show some difference in grammatical structures when compared to human-written items, linguistic complexity results did not differ significantly between tests. Psychometric properties showed only minor differences. These findings lend support to the potential of Automatic Item Generation with LLMs in the context of sentence repetition tasks and might support the process of standardisation in SLA research and testing by enabling parallel test creation.

While immediate feedback on learner language is often discussed in the Second Language Acquisition literature (e.g., Mackey 2006), few systems used in real-life educational settings provide helpful, metalinguistic feedback to learners. In this paper, we present a novel approach leveraging task information to generate the expected range of well-formed and ill-formed variability in learner answers along with the required diagnosis and feedback. We combine this offline generation approach with an online component that matches the actual student answers against the pre-computed hypotheses. The results obtained for a set of 33 thousand answers of 7th grade German high school students learning English show that the approach successfully covers frequent answer patterns. At the same time, paraphrases and content errors require a more flexible alignment approach, for which we are planning to complement the method with the CoMiC approach successfully used for the analysis of reading comprehension answers (Meurers et al., 2011).