Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning

Key points

• The research introduces Binary Bleed, an adapted binary search method that reduces low-rank search complexity for Non-negative Matrix Factorization (NMF), and Hierarchical NMF with automatic latent feature selection (HNMFk), a depth-adaptive topic modeling method that produces interpretable taxonomies guided by subject matter experts.1
• Tensor-Structured Retrieval-Augmented Generation (T-SRAG) dynamically routes queries across retrieval paths.1
• Contrastive alignment maps document and query embeddings to hierarchical topic structures to improve semantic fidelity and reduce hallucinations.1
• Beyond retrieval, tensor-based link prediction identifies and completes missing links in the Knowledge Graph, supporting inference grounded in citation structure.1

Sources (1)

• [1]Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 04:35 PM

  This dissertation presents a scalable architecture for transforming unstructured, domain-specific text into structured knowledge for retrieval and reasoning.

  The research introduces Binary Bleed, an adapted binary search method that reduces low-rank search complexity for Non-negative Matrix Factorization (NMF), and Hierarchical NMF with automatic latent feature selection (HNMFk), a depth-adaptive topic modeling method that produces interpretable taxonomies guided by subject matter experts.

Extractive summary: sentences quoted from the sources.