Design and Appropriation of Knowledge, Chatbot and Other AI Systems
Permanent URI for this collectionhttps://hdl.handle.net/10125/107530
Browse
Recent Submissions
Item type: Item , OER-Chat: An Open Chatbot to Support the Reuse of Open Educational Resources of Introductory Programming(2024-01-03) Deus, William; Barbosa, EllenThis study presents OER-Chat, a chatbot designed for introductory programming. OER-Chat adopts Open Educational Resources (OER) instead of providing textual responses, which is common among other chatbots. Essentially, OER-Chat offers educational materials for introductory programming to address users' doubts or questions, such as slides, courses, or open textbooks. By doing so, it promotes the reuse of these materials and fosters Open Education. We evaluated OER-Chat using a qualitative paradigm. Obtained results demonstrated the efficiency of OER-Chat for the participants and identified areas for future improvement to enhance its performance.Item type: Item , Transforming Generative Large Language Models' Limitations into Strengths using Gestalt: A Synergetic Approach to Mathematical Problem-Solving with Computational Engines(2024-01-03) Dunn, Cayden; Hashemi Tonekaboni, NavidThis paper presents an innovative approach, known as Gestalt, to enhance the mathematical problem-solving capabilities of Generative Large Language Models (GLLMs) while addressing their inherent limitations. Recognizing the inherent structure and discerning strength of GLLMs, the core of our approach strategically offloads computations, deterministic questions, and knowledge retrieval to external tools such as Wolfram Alpha and Python REPL. This critical augmentation not only mitigates GLLMs' variable reliability in these areas but also fortifies their innate strength - understanding the underlying structure of the problems at hand. With this novel implementation, GLLMs can harness the potential of external systems through well-structured queries, enabling them to make significant strides in problem-solving. In a preliminary evaluation, the Gestalt system demonstrates exceptional performance on a portion of the MATH benchmark dataset, achieving a state-of-the-art accuracy of 59.00%. In comparison, GPT-4 achieves an accuracy of 53.9% on the identical dataset. Through our augmentation approach, we aim to transform the limitations of GLLMs into their strengths, opening up exciting new possibilities not only in advanced mathematical problem-solving but also in various deterministic tasks such as medical diagnosis.Item type: Item , Introduction to the Minitrack on Design and Appropriation of Knowledge, Chatbot and Other AI Systems(2024-01-03) Holford, W. David; Hadaya, Pierre; Smolnik, Stefan