Publication Date

2025

Document Type

Thesis

Committee Members

Cogan Shimizu, Ph.D. (Advisor); Wen Zhang, Ph.D. (Committee Member); Krishnaprasad Thirunarayan, Ph.D. (Committee Member)

Degree Name

Master of Science (MS)

Abstract

Explainability, interpretability and adaptability (EIA) remain three central motivations for next-generation Artificial Intelligence (AI), especially as Large Language Models (LLMs) continue to engage with ever-increasing knowledge bodies. As the landscape pushes toward controllable agentic Retrieval-Augmented Generation (RAG) systems where AI agents engage in iterative, guided reasoning, a critical question arises as to the extent to which the knowledge design itself shapes these models' reasoning behavior. This work conducts a systematic evaluation of how different conceptualizations and representation of the identical knowledge affect an LLM's path-based reasoning capabilities. Through the introduction of controlled variations along graph structural complexity, linguistic and semantic design dimensions, the study isolates how design factors propagate through the interpretation and reasoning pipeline. Findings posit ontology engineering as a first-order determinant and illustrate how decisions made during knowledge construction may have direct implications for stability and alignment of future neurosymbolic architectures.

Page Count

104

Department or Program

Department of Computer Science and Engineering

Year Degree Awarded

2025

ORCID ID

0009-0000-2287-1198


Share

COinS