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.authorDunn, Cayden
dc.contributor.authorHashemi Tonekaboni, Navid
dc.date.accessioned2023-12-26T18:46:02Z
dc.date.available2023-12-26T18:46:02Z
dc.date.issued2024-01-03
dc.identifier.doi10.24251/HICSS.2024.622
dc.identifier.isbn978-0-9981331-7-1
dc.identifier.other85bd623e-828f-4fc3-959b-6c3392a0a00d
dc.identifier.urihttps://hdl.handle.net/10125/107007
dc.language.isoeng
dc.relation.ispartofProceedings of the 57th Hawaii International Conference on System Sciences
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectDesign and Appropriation of Knowledge, Chatbot and Other AI Systems
dc.subjectartificial intelligence (ai)
dc.subjectcode interpreter
dc.subjectgenerative large language models (gllms)
dc.subjectmathematical problem-solving
dc.subjectnatural language processing (nlp)
dc.titleTransforming Generative Large Language Models' Limitations into Strengths using Gestalt: A Synergetic Approach to Mathematical Problem-Solving with Computational Engines
dc.typeConference Paper
dc.type.dcmiText
dcterms.abstractThis 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.extent10 pages
prism.startingpage5185

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
0509.pdf
Size:
549.21 KB
Format:
Adobe Portable Document Format
Download

Collections

Design and Appropriation of Knowledge, Chatbot and Other AI Systems