A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods

Abstract

The rapid development of artificial intelligence has led to marked progress in the field. One interesting direction for research is whether Large Language Models (LLMs) can be integrated with structured knowledge-based systems. This approach aims to combine the generative language understanding of LLMs and the precise knowledge representation systems by which they are integrated. This article surveys the relationship between LLMs and knowledge bases, looks at how they can be applied in practice, and discusses related technical, operational, and ethical challenges. Utilizing a comprehensive examination of the literature, the study both identifies important issues and assesses existing solutions. It demonstrates the merits of incorporating generative AI into structured knowledge-base systems concerning data contextualization, model accuracy, and utilization of knowledge resources. The findings give a full list of the current situation of research, point out the main gaps, and propose helpful paths to take. These insights contribute to advancing AI technologies and support their practical deployment across various sectors.

References in corpus (42)

• Generative Adversarial Networks
• Training language models to follow instructions with human feedback
• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• ChatGPT is not all you need. A State of the Art Review of large Generative AI models
• Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
• DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
• A Performance Study of LLM-Generated Code on Leetcode
• A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods
• DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders
• A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges
• Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
• Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey
• Unveiling LLM Evaluation Focused on Metrics: Challenges and Solutions
• A Survey on Large Language Models with some Insights on their Capabilities and Limitations
• The Chronicles of RAG: The Retriever, the Chunk and the Generator
• LLM Agents can Autonomously Exploit One-day Vulnerabilities
• A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
• KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph
• Medical mT5: An Open-Source Multilingual Text-to-Text LLM for The Medical Domain
• BioRAG: A RAG-LLM Framework for Biological Question Reasoning
• Sentiment Analysis through LLM Negotiations
• REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models
• Focus Agent: LLM-Powered Virtual Focus Group
• Combining Knowledge Graphs and Large Language Models
• Synthetic Query Generation using Large Language Models for Virtual Assistants
• Integrating UMLS Knowledge into Large Language Models for Medical Question Answering
• WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs
• Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge
• KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation
• Language Models for Code Optimization: Survey, Challenges and Future Directions
• Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation
• SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs
• Chain-of-Knowledge: Integrating Knowledge Reasoning into Large Language Models by Learning from Knowledge Graphs
• Topological or not? A unified pattern description in the one-dimensional anisotropic quantum XY model with a transverse field
• LLMs Meet Multimodal Generation and Editing: A Survey
• Meta Reasoning for Large Language Models
• PAS: Data-Efficient Plug-and-Play Prompt Augmentation System
• Towards Efficient Large Language Models for Scientific Text: A Review
• Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models
• Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching
• Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods

Cited by in corpus (1)

• A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods