SOTAVerified

RAG

Retrieval-Augmented Generation (RAG) is a task that combines the strengths of both retrieval-based models and generation-based models. In this approach, a retrieval system selects relevant documents or passages from a large corpus, and a generation model, typically a neural language model, uses the retrieved information to generate a response. This method enhances the accuracy and coherence of generated text, especially in tasks requiring detailed knowledge or long context handling.

RAG is particularly useful in open-domain question answering, knowledge-grounded dialogue, and summarization tasks. The retrieval step helps the model to access and incorporate external information, making it less reliant on memorized knowledge and better suited for generating responses based on the latest or domain-specific information.

The performance of RAG systems is usually measured using metrics such as precision, recall, F1 score, BLEU score, and exact match. Some popular datasets for evaluating RAG models include Natural Questions, MS MARCO, TriviaQA, and SQuAD.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2001–2025 of 2111 papers

TitleStatusHype
Health-LLM: Personalized Retrieval-Augmented Disease Prediction System—0
RAG-Fusion: a New Take on Retrieval-Augmented Generation—0
Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems—0
Weaver: Foundation Models for Creative Writing—0
CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language ModelsCode3
LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and DistillationCode2
Development and Testing of Retrieval Augmented Generation in Large Language Models -- A Case Study Report—0
Development and Testing of a Novel Large Language Model-Based Clinical Decision Support Systems for Medication Safety in 12 Clinical Specialties—0
Corrective Retrieval Augmented GenerationCode3
Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately—0
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop QueriesCode3
Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language ModelsCode2
A RAG-based Question Answering System Proposal for Understanding Islam: MufassirQAS LLM—0
From RAG to QA-RAG: Integrating Generative AI for Pharmaceutical Regulatory Compliance ProcessCode1
The Power of Noise: Redefining Retrieval for RAG SystemsCode2
UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems—0
Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognition—0
Evaluating and Enhancing Large Language Models Performance in Domain-specific Medicine: Osteoarthritis Management with DocOA—0
Prompt-RAG: Pioneering Vector Embedding-Free Retrieval-Augmented Generation in Niche Domains, Exemplified by Korean Medicine—0
ChatQA: Surpassing GPT-4 on Conversational QA and RAG—0
Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task—0
RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture—0
Graph database while computationally efficient filters out quickly the ESG integrated equities in investment management—0
The Chronicles of RAG: The Retriever, the Chunk and the Generator—0
Bridging the Preference Gap between Retrievers and LLMs—0
Show:102550
← PrevPage 81 of 85Next →

No leaderboard results yet.