Vladislav Belov

Join us for an informative tech talk where we will delve into the development of domain-specific translation models, comprehension check generation models, and other advanced AI models for educational platforms. We will discuss how we leveraged state-of-the-art language models, such as GPT-3 and others, to build these models from the ground up, tailoring them to meet the specific needs and challenges of the education domain. We will also share the techniques we used to engineer prompts for state-of-the-art models and fine-tune weaker models to achieve the quality of more expensive ones. Additionally, we will cover metrics calculation and the costs involved in developing these models. Don't miss this opportunity to gain valuable insights into the exciting possibilities of AI and advanced language models in education.