The Design and Implementation of AI Partner in Supporting Foreign Language Teaching and Assessment
We plan to focus on AI training to improve students' performance on the Oral Proficiency Interview (OPI). We will train the AI on the structure of the OPI using ACTFL proficiency guidelines and design prompts that simulate a natural, contextual target language environment.
The existing CFLingo platform supports conversations between Chinese as a Foreign Language (CFL) students and OpenAIs ChatGPT LLM. The platform facilitates a variety of exercises, including debates, roleplays, sentence creation, essay outlining, and essay drafting. We are currently in the process of augmenting the scripts supporting our existing CFLingo platform to use audio as both an input and output as well as text. The existing platform uses OpenAIs GPT-4-Omni LLM, which only uses text for input and output. However there is now an available model, GPT-4-Omni-Audio-Preview that can use audio in addition to text for input and output using the same "chat completions" API end point as the standard 4 Omni model. However, we need to slightly restructure the messages being sent and received by our platform as the model requires additional parameters for audio settings and also returns audio as part of its response.
