# Domain-Specific Knowledge Graphs in RAG-Enhanced Healthcare LLMs

arXiv: https://arxiv.org/abs/2601.15429 · HTML: https://mlsanity.com/paper/2601.15429/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 32 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [Biomedical knowledge graph-optimized prompt generation for large language models](https://mlsanity.com/paper/2311.17330/) (2023)
- [Knowledge Graph-extended Retrieval Augmented Generation for Question Answering](https://mlsanity.com/paper/2504.08893/) (2025)
- [Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling](https://mlsanity.com/paper/2509.17289/) (2025)
- [FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs](https://mlsanity.com/paper/2501.09957/) (2025)
- [Trustworthy Medical Question Answering: An Evaluation-Centric Survey](https://mlsanity.com/paper/2506.03659/) (2025)
- [MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generation](https://mlsanity.com/paper/2508.03553/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) generate fluent answers but can struggle with trustworthy, domain-specific reasoning. We evaluate whether domain knowledge graphs (KGs) improve Retrieval-Augmented Generation (RAG) for healthcare by constructing three PubMed-derived graphs: mathbbG1 (T2DM), mathbbG2 (Alzheimer's disease), and mathbbG3 (AD+T2DM). We design two probes: Probe 1 targets merged AD T2DM knowledge, while Probe 2 targets the intersection of mathbbG1 and mathbbG2. Seven instruction-tuned LLMs are tested across retrieval sources No-RAG, mathbbG1, mathbbG2, mathbbG1 + mathbbG2, mathbbG3, mathbbG1+mathbbG2 + mathbbG3 and three decoding temperatures. Results show that scope alignment between probe and KG is decisive: precise, scope-matched retrieval (notably mathbbG2) yields the most consistent gains, whereas indiscriminate graph unions often introduce distractors that reduce accuracy. Larger models frequently match or exceed KG-RAG with a No-RAG baseline on Probe 1, indicating strong parametric priors, whereas smaller/mid-sized models benefit more from well-scoped retrieval. Temperature plays a secondary role; higher values rarely help. We conclude that precision-first, scope-matched KG-RAG is preferable to breadth-first unions, and we outline practical guidelines for graph selection, model sizing, and retrieval/reranking. Code and Data available here - https://github.com/sydneyanuyah/RAGComparison