Retrieval-Augmented Generation for Large Language Models: A Survey

Abstract

Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of external databases. This comprehensive review paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG. It meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval, the generation and the augmentation techniques. The paper highlights the state-of-the-art technologies embedded in each of these critical components, providing a profound understanding of the advancements in RAG systems. Furthermore, this paper introduces up-to-date evaluation framework and benchmark. At the end, this article delineates the challenges currently faced and points out prospective avenues for research and development.

Ongoing Work

Cited by in corpus (39)

• Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
• The opportunities and risks of large language models in mental health
• Materials science in the era of large language models: a perspective
• Tool Learning with Large Language Models: A Survey
• A Comprehensive Survey on Integrating Large Language Models with Knowledge-Based Methods
• Leveraging LLMs for the Quality Assurance of Software Requirements
• Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis
• From Intention To Implementation: Automating Biomedical Research via LLMs
• A Unified Industrial Large Knowledge Model Framework in Industry 4.0 and Smart Manufacturing
• Generating Test Scenarios from NL Requirements using Retrieval-Augmented LLMs: An Industrial Study
• QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance
• OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Design
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models
• Generative Information Retrieval Evaluation
• Agents for self-driving laboratories applied to quantum computing
• Securing RAG: A Risk Assessment and Mitigation Framework
• LAMBDA: A Large Model Based Data Agent
• Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets
• Leveraging Lecture Content for Improved Feedback: Explorations with GPT-4 and Retrieval Augmented Generation
• Statically Contextualizing Large Language Models with Typed Holes
• The Use of Artificial Intelligence in Military Intelligence: An Experimental Investigation of Added Value in the Analysis Process
• A Simplified Retriever to Improve Accuracy of Phenotype Normalizations by Large Language Models
• Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intents
• SlideItRight: Using AI to Find Relevant Slides and Provide Feedback for Open-Ended Questions
• Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
• Generative AI in Health Economics and Outcomes Research: A Taxonomy of Key Definitions and Emerging Applications, an ISPOR Working Group Report
• The Viability of Crowdsourcing for RAG Evaluation
• EvidenceMap: Learning Evidence Analysis to Unleash the Power of Small Language Models for Biomedical Question Answering
• LLM-based Multimodal Feedback Produces Equivalent Learning and Better Student Perceptions than Educator Feedback
• Simplifying Data Integration: SLM-Driven Systems for Unified Semantic Queries Across Heterogeneous Databases
• Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval
• The benefits of query-based KGQA systems for complex and temporal questions in LLM era
• How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
• A Roadmap for Tamed Interactions with Large Language Models
• Context Aware AI Assistant and AR Interface for Lunar Extravehicular Activity (EVA) Procedural Guidance
• MultiMend: Multilingual Program Repair with Context Augmentation and Multi-Hunk Patch Generation
• Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations
• Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&A