Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Renzella, Jake"'
This paper investigates supervised fine-tuning of large language models (LLMs) to improve their pedagogical alignment in computing education, addressing concerns that LLMs may hinder learning outcomes. The project utilised a proprietary dataset of 2,
Externí odkaz:
http://arxiv.org/abs/2411.01765
This paper introduces DCC Sidekick, a web-based conversational AI tool that enhances an existing LLM-powered C/C++ compiler by generating educational programming error explanations. The tool seamlessly combines code display, compile- and run-time err
Externí odkaz:
http://arxiv.org/abs/2408.02378
While deep learning approaches represent the state-of-the-art of natural language processing (NLP) today, classical algorithms and approaches still find a place in NLP textbooks and courses of recent years. This paper discusses the perspectives of co
Externí odkaz:
http://arxiv.org/abs/2405.09854
In the challenging field of introductory programming, high enrollments and failure rates drive us to explore tools and systems to enhance student outcomes, especially automated tools that scale to large cohorts. This paper presents and evaluates the
Externí odkaz:
http://arxiv.org/abs/2308.11873
Publikováno v:
In Computers and Education: Artificial Intelligence 2022 3
Autor:
Renzella, Jake, Rozova, Vlada
Publikováno v:
Conversation (Conversation Media Group Ltd); 5/20/2024, p1-1, 1p, 3 Color Photographs