Automatic Generation of Corpus-Based Exercises Using Generative AI

Abstract

This study explores the automatic generation of corpus-based language exercises using a generative AI model Corpus Linguist. It focuses on the interaction between the language model and corpus data, detailing a workflow in which collocation and translation patterns are extracted from a tagged corpus and structured prompts are constructed to guide the model in producing sentence-level exercises. The generated exercises reveal both the potential and the current limitations of AI-driven approaches. Challenges include inconsistency in corpus data use, and choosing appropriate translation equivalents. These observations highlight the necessity of careful design and critical evaluation when integrating generative models with corpus-based language materials. By analysing these processes from a computational linguistics perspective, this study contributes to understanding how generative AI can interact with structured linguistic data, informing future applications in automated language resources.