Biomedical knowledge graph-optimized prompt generation for large language models
- URL: http://arxiv.org/abs/2311.17330v2
- Date: Mon, 13 May 2024 22:48:04 GMT
- Title: Biomedical knowledge graph-optimized prompt generation for large language models
- Authors: Karthik Soman, Peter W Rose, John H Morris, Rabia E Akbas, Brett Smith, Braian Peetoom, Catalina Villouta-Reyes, Gabriel Cerono, Yongmei Shi, Angela Rizk-Jackson, Sharat Israni, Charlotte A Nelson, Sui Huang, Sergio E Baranzini,
- Abstract summary: Large Language Models (LLMs) are being adopted at an unprecedented rate, yet still face challenges in knowledge-intensive domains like biomedicine.
Here, we introduce a token-optimized and robust Knowledge Graph-based Retrieval Augmented Generation framework.
- Score: 1.6658478064349376
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) are being adopted at an unprecedented rate, yet still face challenges in knowledge-intensive domains like biomedicine. Solutions such as pre-training and domain-specific fine-tuning add substantial computational overhead, requiring further domain expertise. Here, we introduce a token-optimized and robust Knowledge Graph-based Retrieval Augmented Generation (KG-RAG) framework by leveraging a massive biomedical KG (SPOKE) with LLMs such as Llama-2-13b, GPT-3.5-Turbo and GPT-4, to generate meaningful biomedical text rooted in established knowledge. Compared to the existing RAG technique for Knowledge Graphs, the proposed method utilizes minimal graph schema for context extraction and uses embedding methods for context pruning. This optimization in context extraction results in more than 50% reduction in token consumption without compromising the accuracy, making a cost-effective and robust RAG implementation on proprietary LLMs. KG-RAG consistently enhanced the performance of LLMs across diverse biomedical prompts by generating responses rooted in established knowledge, accompanied by accurate provenance and statistical evidence (if available) to substantiate the claims. Further benchmarking on human curated datasets, such as biomedical true/false and multiple-choice questions (MCQ), showed a remarkable 71% boost in the performance of the Llama-2 model on the challenging MCQ dataset, demonstrating the framework's capacity to empower open-source models with fewer parameters for domain specific questions. Furthermore, KG-RAG enhanced the performance of proprietary GPT models, such as GPT-3.5 and GPT-4. In summary, the proposed framework combines explicit and implicit knowledge of KG and LLM in a token optimized fashion, thus enhancing the adaptability of general-purpose LLMs to tackle domain-specific questions in a cost-effective fashion.
Related papers
- GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation [84.41557981816077]
We introduce GFM-RAG, a novel graph foundation model (GFM) for retrieval augmented generation.
GFM-RAG is powered by an innovative graph neural network that reasons over graph structure to capture complex query-knowledge relationships.
It achieves state-of-the-art performance while maintaining efficiency and alignment with neural scaling laws.
arXiv Detail & Related papers (2025-02-03T07:04:29Z) - Knowledge Hierarchy Guided Biological-Medical Dataset Distillation for Domain LLM Training [10.701353329227722]
We propose a framework that automates the distillation of high-quality textual training data from the extensive scientific literature.
Our approach self-evaluates and generates questions that are more closely aligned with the biomedical domain.
Our approach substantially improves question-answering tasks compared to pre-trained models from the life sciences domain.
arXiv Detail & Related papers (2025-01-25T07:20:44Z) - FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs [17.477161619378332]
We propose a novel flexible modular KG-RAG framework, termed FRAG, which synergizes the advantages of both approaches.
By using the query text instead of the Knowledge Graph, FRAG improves retrieval quality while maintaining flexibility.
arXiv Detail & Related papers (2025-01-17T05:19:14Z) - LLaVA Needs More Knowledge: Retrieval Augmented Natural Language Generation with Knowledge Graph for Explaining Thoracic Pathologies [3.2221734920470797]
We propose a Vision-Language framework augmented with a Knowledge Graph (KG)-based datastore to generate Natural Language Explanations (NLEs) for medical images.
Our framework employs a KG-based retrieval mechanism that not only improves the precision of the generated explanations but also preserves data privacy by avoiding direct data retrieval.
These frameworks are validated on the MIMIC-NLE dataset, where they achieve state-of-the-art results.
arXiv Detail & Related papers (2024-10-07T04:59:08Z) - Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval [61.70489848327436]
KARE is a novel framework that integrates knowledge graph (KG) community-level retrieval with large language models (LLMs) reasoning.
Extensive experiments demonstrate that KARE outperforms leading models by up to 10.8-15.0% on MIMIC-III and 12.6-12.7% on MIMIC-IV for mortality and readmission predictions.
arXiv Detail & Related papers (2024-10-06T18:46:28Z) - Fact Finder -- Enhancing Domain Expertise of Large Language Models by Incorporating Knowledge Graphs [2.7386111894524]
We introduce a hybrid system that augments Large Language Models with domain-specific knowledge graphs (KGs)
We evaluate our system on a curated dataset of 69 samples, achieving a precision of 78% in retrieving correct KG nodes.
Our findings indicate that the hybrid system surpasses a standalone LLM in accuracy and completeness.
arXiv Detail & Related papers (2024-08-06T07:45:05Z) - SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation [50.26966969163348]
Large Language Models (LLMs) have shown great potential in the biomedical domain with the advancement of retrieval-augmented generation (RAG)
Existing retrieval-augmented approaches face challenges in addressing diverse queries and documents, particularly for medical knowledge queries.
We propose Self-Rewarding Tree Search (SeRTS) based on Monte Carlo Tree Search (MCTS) and a self-rewarding paradigm.
arXiv Detail & Related papers (2024-06-17T06:48:31Z) - HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs Responses [20.635793525894872]
We develop a Hypothesis Knowledge Graph Enhanced (HyKGE) framework to improve the accuracy and reliability of Large Language Models (LLMs)
Specifically, HyKGE explores the zero-shot capability and the rich knowledge of LLMs with Hypothesis Outputs to extend feasible exploration directions in the KGs.
Experiments on two Chinese medical multiple-choice question datasets and one Chinese open-domain medical Q&A dataset with two LLM turbos demonstrate the superiority of HyKGE in terms of accuracy and explainability.
arXiv Detail & Related papers (2023-12-26T04:49:56Z) - Mitigating Large Language Model Hallucinations via Autonomous Knowledge
Graph-based Retrofitting [51.7049140329611]
This paper proposes Knowledge Graph-based Retrofitting (KGR) to mitigate factual hallucination during the reasoning process.
Experiments show that KGR can significantly improve the performance of LLMs on factual QA benchmarks.
arXiv Detail & Related papers (2023-11-22T11:08:38Z) - Knowledge-Augmented Reasoning Distillation for Small Language Models in
Knowledge-Intensive Tasks [90.11273439036455]
Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks.
We propose Knowledge-Augmented Reasoning Distillation (KARD), a novel method that fine-tunes small LMs to generate rationales from LLMs with augmented knowledge retrieved from an external knowledge base.
We empirically show that KARD significantly improves the performance of small T5 and GPT models on the challenging knowledge-intensive reasoning datasets.
arXiv Detail & Related papers (2023-05-28T13:00:00Z) - Scientific Language Models for Biomedical Knowledge Base Completion: An
Empirical Study [62.376800537374024]
We study scientific LMs for KG completion, exploring whether we can tap into their latent knowledge to enhance biomedical link prediction.
We integrate the LM-based models with KG embedding models, using a router method that learns to assign each input example to either type of model and provides a substantial boost in performance.
arXiv Detail & Related papers (2021-06-17T17:55:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.