Исследование эффективности промпт-инжиниринга и квантованных LLM в создании структуры академических курсов
Polina Shnaider, Anastasiia Chernysheva, Anna E. Nikiforova, Антон Игоревич Говоров, Maksim Khlopotov · Computer Tools in Education · 2024
This article presents the outcomes of an experiment employing large language models (LLMs) in the development of university course structures. Various prompt engineering methods, including zero-shot, few-shot, chain-of-thought, and tree-of-thought, were employed to formulate queries to LLMs. Primarily, quantized models such as mistral-7b-instruct, mixtral-8x7b-instruct, openchat_3.5, saiga2_13b, starling-lm-7b-alpha, tinyllama, among others, were utilized for the experiment. The generated course structures were compared with data obtained from ChatGPT-4. Models openchat_3.5.q5_k_m and starling-lm-7b-alpha.q5_k_m demonstrated comparable quality in generating educational program structures to ChatGPT-4. The experiment underscores the potential applications of LLMs in the field of education and highlights promising directions for further research.