Modeling the Chaotic Semantic States of Generative Artificial Intelligence (AI): A Quantum Mechanics Analogy Approach

Simple item page
dc.citation.issue6
dc.citation.volume16
dc.contributor.authorLiu T
dc.contributor.authorMcIntosh TR
dc.contributor.authorSusnjak T
dc.contributor.authorWatters P
dc.contributor.authorHalgamuge MN
dc.date.accessioned2025-10-27T21:53:04Z
dc.date.available2025-10-27T21:53:04Z
dc.date.issued2025-12-01
dc.description.abstractGenerative artificial intelligence (AI) models have revolutionized intelligent systems by enabling machines to produce human-like content across diverse domains. However, their outputs often exhibit unpredictability due to complex and opaque internal semantic states, posing challenges for reliability in real-world applications. In this paper, we introduce the AI Uncertainty Principle, a novel theoretical framework inspired by quantum mechanics, to model and quantify the inherent unpredictability in generative AI outputs. By drawing parallels with the uncertainty principle and superposition, we formalize the trade-off between the precision of internal semantic states and output variability. Through comprehensive experiments involving state-of-the-art models and a variety of prompt designs, we analyze how factors such as specificity, complexity, tone, and style influence model behavior. Our results demonstrate that carefully engineered prompts can significantly enhance output predictability and consistency, while excessive complexity or irrelevant information can increase uncertainty. We also show that ensemble techniques, such as Sigma-weighted aggregation across models and prompt variations, effectively improve reliability. Our findings have profound implications for the development of intelligent systems, emphasizing the critical role of prompt engineering and theoretical modeling in creating AI technologies that perceive, reason, and act predictably in the real world.
dc.description.confidentialfalse
dc.edition.editionDecember 2025
dc.identifier.citationLiu T, McIntosh TR, Susnjak T, Watters P, Halgamuge MN. (2025). Modeling the Chaotic Semantic States of Generative Artificial Intelligence (AI): A Quantum Mechanics Analogy Approach. ACM Transactions on Intelligent Systems and Technology. 16. 6.
dc.identifier.doi10.1145/3757927
dc.identifier.eissn2157-6912
dc.identifier.elements-typejournal-article
dc.identifier.issn2157-6904
dc.identifier.number126
dc.identifier.urihttps://mro.massey.ac.nz/handle/10179/73727
dc.languageEnglish
dc.publisherAssociation for Computing Machinery
dc.publisher.urihttps://dl.acm.org/doi/10.1145/3757927
dc.relation.isPartOfACM Transactions on Intelligent Systems and Technology
dc.rights(c) The author/sen
dc.rights.licenseCC BY-NC-NDen
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectComplexity
dc.subjectGenerative Artificial Intelligence
dc.subjectOutput Variability
dc.subjectPrompt Engineering
dc.subjectUncertainty
dc.titleModeling the Chaotic Semantic States of Generative Artificial Intelligence (AI): A Quantum Mechanics Analogy Approach
dc.typeJournal article
pubs.elements-id502697
pubs.organisational-groupOther
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
502697 PDF.pdf
Size:
1.73 MB
Format:
Adobe Portable Document Format
Description:
Published version.pdf
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
9.22 KB
Format:
Plain Text
Description:
Download
Collections
Journal Articles