Разработка интерфейса виртуального ассистента преподавателя на основе технологий вызова функций и инженерии инструкций для больших языковых моделей

Человек: образ и сущность. Гуманитарные аспекты. 2025. Vol. 2. No. 62. P. 203–214.

Фирсанова В. И.

Abstract. The paper highlights prompt engineering in academic setting to reduce plagiarism and increase students' interest. The research problem is the lack of a unified methodology for using artificial intelligence in education. The paper aims to create a generative artificial intelligence user interface, the Virtual Teaching Assistant. Teachers were interviewed, the first collection of presets for prompt engineering in an academic environment was developed, and a virtual assistant interface was created. The qualitative analysis revealed that educators are interested in applying large language models to developing assessment materials, adapting learning content for providing accessibility, and creating education illustrations. However, the study identified challenges, including hallucinations in generated content and the risk of plagiarism. The study resulted in the development of a virtual teaching assistant interface with features such as prompt presets, custom guardrails, and plagiarism detection. The prompt presets are simplified templates for generating assignments, quizzes, and educational materials. Guardrails are safety controls that ensure ethical and inclusive content generation. Plagiarism checker is a function that detects Al-generated content through analyzing students' submissions using neural network weights.

Keywords: educational technologies, методология преподавания, гуманитарные образовательные технологии, Виртуальный ассистент, virtual assistant, промпт-инжиниринг, генеративный искусственный интеллект, teaching methodology, prompt engineering, generative artificial intelligence