# Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning

arXiv: https://arxiv.org/abs/2610.08894 · HTML: https://mlsanity.com/paper/2610.08894/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 250 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 30 of 34)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [PaperQA: Retrieval-Augmented Generative Agent for Scientific Research](https://mlsanity.com/paper/2312.07559/) (2023)
- [Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs](https://mlsanity.com/paper/2404.07103/) (2024)
- [The Semantic Scholar Open Data Platform](https://mlsanity.com/paper/2301.10140/) (2023)
- [LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain](https://mlsanity.com/paper/2408.10343/) (2024)
- [HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction](https://mlsanity.com/paper/2408.04948/) (2024)
- [KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering](https://mlsanity.com/paper/2110.04330/) (2021)
- [KG-RAG: Bridging the Gap Between Knowledge and Creativity](https://mlsanity.com/paper/2405.12035/) (2024)
- [Biomedical knowledge graph-optimized prompt generation for large language models](https://mlsanity.com/paper/2311.17330/) (2023)
- [HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases](https://mlsanity.com/paper/2412.16311/) (2024)
- [When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively](https://mlsanity.com/paper/2404.19705/) (2024)
- [Recent Developments in Boolean Matrix Factorization](https://mlsanity.com/paper/2012.03127/) (2020)
- [CaseLink: Inductive Graph Learning for Legal Case Retrieval](https://mlsanity.com/paper/2403.17780/) (2024)
- [BIOS: An Algorithmically Generated Biomedical Knowledge Graph](https://mlsanity.com/paper/2203.09975/) (2022)
- [Similar Cases Recommendation using Legal Knowledge Graphs](https://mlsanity.com/paper/2107.04771/) (2021)
- [Confidence from Invariance to Image Transformations](https://mlsanity.com/paper/1804.00657/) (2018)
- [Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction](https://mlsanity.com/paper/2312.03022/) (2023)
- [Guided Semi-Supervised Non-negative Matrix Factorization on Legal Documents](https://mlsanity.com/paper/2201.13324/) (2022)
- [FedSPLIT: One-Shot Federated Recommendation System Based on Non-negative Joint Matrix Factorization and Knowledge Distillation](https://mlsanity.com/paper/2205.02359/) (2022)
- [Modified Binary Search Algorithm](https://mlsanity.com/paper/1406.1677/) (2014)
- [Automatic Knowledge Graph Construction for Judicial Cases](https://mlsanity.com/paper/2404.09416/) (2024)

## Abstract (arXiv)

This dissertation presents a scalable architecture for transforming unstructured, domain-specific text into structured knowledge for retrieval and reasoning. It integrates semi-automatic corpus curation, semantic structuring, retrieval, and inference into an interpretable pipeline. 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. These representations populate a typed Knowledge Graph and a semantically aligned Vector Store containing extracted latent features, synchronized through an event-driven substrate. Tensor-Structured Retrieval-Augmented Generation (T-SRAG) dynamically routes queries across retrieval paths. Contrastive alignment maps document and query embeddings to hierarchical topic structures to improve semantic fidelity and reduce hallucinations. Beyond retrieval, tensor-based link prediction identifies and completes missing links in the Knowledge Graph, supporting inference grounded in citation structure. Applications across cybersecurity, law, materials science, and healthcare demonstrate improvements in retrieval precision, early trend detection, hypothesis generation, and hallucination mitigation. The dissertation provides a deployable, modular foundation for trustworthy, domain-specific AI systems that retrieve and reason over structured knowledge.