Saved in:
Bibliographic Details
Main Authors: Lecu, Alexandru, Groza, Adrian, Hawizy, Lezan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.11108
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909496121491456
author Lecu, Alexandru
Groza, Adrian
Hawizy, Lezan
author_facet Lecu, Alexandru
Groza, Adrian
Hawizy, Lezan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_11108
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge Graph-Driven Retrieval-Augmented Generation: Integrating Deepseek-R1 with Weaviate for Advanced Chatbot Applications
Lecu, Alexandru
Groza, Adrian
Hawizy, Lezan
Computation and Language
Artificial Intelligence
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.
title Knowledge Graph-Driven Retrieval-Augmented Generation: Integrating Deepseek-R1 with Weaviate for Advanced Chatbot Applications
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.11108