Knowledge Graph-Driven Retrieval-Augmented Generation: Integrating Deepseek-R1 with Weaviate for Advanced Chatbot Applications
On the map: Retrieval-augmented generation → Medical and biomedical RAG
Abstract (arXiv)
Large language models (LLMs) have significantly advanced the field of natural language generation. However, they frequently generate unverified outputs, which compromises their reliability in critical applications. In this study, we propose an innovative framework that combines structured biomedical knowledge with LLMs through a retrieval-augmented generation technique. Our system develops a thorough knowledge graph by identifying and refining causal relationships and named entities from medical abstracts related to age-related macular degeneration (AMD). Using a vector-based retrieval process and a locally deployed language model, our framework produces responses that are both contextually relevant and verifiable, with direct references to clinical evidence. Experimental results show that this method notably decreases hallucinations, enhances factual precision, and improves the clarity of generated responses, providing a robust solution for advanced biomedical chatbot applications.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 5 of its 17 references that are in the map. First posted on arXiv 16 Feb 2025.
Builds on
5 of 17 references.
References · 5
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2023Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluationcited by 69
- 2023Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modelingcited by 56
- 2023Ontology engineering with Large Language Modelscited by 17
Built on by
Citing papers per year: 2025: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Addressing accuracy and hallucination of LLMs in Alzheimer's disease research through knowledge graphs
- 2023Biomedical knowledge graph-optimized prompt generation for large language models
- 2024Benchmarking Retrieval-Augmented Large Language Models in Biomedical NLP: Application, Robustness, and Self-Awareness
- 2025HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks
- 2024Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge
- 2025A Retrieval-Augmented Knowledge Mining Method with Deep Thinking LLMs for Biomedical Research and Clinical Support
- 2023HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses
- 2024Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Models