Transforming Generative Large Language Models' Limitations into Strengths using Gestalt: A Synergetic Approach to Mathematical Problem-Solving with Computational Engines

Simple item page
dc.contributor.author Dunn, Cayden
dc.contributor.author Hashemi Tonekaboni, Navid
dc.date.accessioned 2023-12-26T18:46:02Z
dc.date.available 2023-12-26T18:46:02Z
dc.date.issued 2024-01-03
dc.identifier.isbn 978-0-9981331-7-1
dc.identifier.other 85bd623e-828f-4fc3-959b-6c3392a0a00d
dc.identifier.uri https://hdl.handle.net/10125/107007
dc.language.iso eng
dc.relation.ispartof Proceedings of the 57th Hawaii International Conference on System Sciences
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject Design and Appropriation of Knowledge, Chatbot and Other AI Systems
dc.subject artificial intelligence (ai)
dc.subject code interpreter
dc.subject generative large language models (gllms)
dc.subject mathematical problem-solving
dc.subject natural language processing (nlp)
dc.title Transforming Generative Large Language Models' Limitations into Strengths using Gestalt: A Synergetic Approach to Mathematical Problem-Solving with Computational Engines
dc.type Conference Paper
dc.type.dcmi Text
dcterms.abstract This 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.
dcterms.extent 10 pages
prism.startingpage 5185
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
0509.pdf
Size:
549.21 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Design and Appropriation of Knowledge, Chatbot and Other AI Systems