Dissertation details AI for structured knowledge retrieval and reasoning

This dissertation introduces a novel architecture for transforming unstructured domain-specific text into structured knowledge for retrieval and reasoning. It presents Binary Bleed, an adapted binary search method for Non-negative Matrix Factorization (NMF), and Hierarchical NMF with automatic latent feature selection (HNMFk) for depth-adaptive topic modeling. These methods populate a knowledge graph and vector store, enabling Tensor-Structured Retrieval-Augmented Generation (T-SRAG) for dynamic query routing and improved semantic fidelity. Applications in cybersecurity, law, materials science, and healthcare demonstrate enhanced retrieval precision, trend detection, and hallucination mitigation. AI

IMPACT Introduces methods to improve the accuracy and interpretability of AI systems in specialized domains.

RANK_REASON The item is an arXiv preprint detailing novel methods for AI-driven knowledge retrieval and reasoning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

• alphaXiv
• Binary Bleed
• CatalyzeX Code Finder for Papers
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hierarchical NMF with automatic latent feature selection
• HNMFk
• Hugging Face
• Influence Flower
• knowledge graph
• Litmaps
• non-negative matrix factorization
• ScienceCast
• scite Smart Citations
• Tensor-Structured Retrieval-Augmented Generation
• T-SRAG
• vector database

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →