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 1726–1750 of 2111 papers

TitleStatusHype
NV-Retriever: Improving text embedding models with effective hard-negative mining—0
MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation—0
RadioRAG: Factual large language models for enhanced diagnostics in radiology using online retrieval augmented generationCode0
An Empirical Comparison of Video Frame Sampling Methods for Multi-Modal RAG Retrieval—0
An Empirical Study of Retrieval Augmented Generation with Chain-of-Thought—0
Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation—0
AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs—0
Golden-Retriever: High-Fidelity Agentic Retrieval Augmented Generation for Industrial Knowledge Base—0
Automatic Generation of Fashion Images using Prompting in Generative Machine Learning ModelsCode0
Differential Privacy of Cross-Attention with Provable Guarantee—0
Retrieval Augmented Generation Integrated Large Language Models in Smart Contract Vulnerability Detection—0
Unipa-GPT: Large Language Models for university-oriented QA in ItalianCode0
ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities—0
Adversarial Databases Improve Success in Retrieval-based Large Language Models—0
Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models—0
Retrieval-Augmented Generation for Natural Language Processing: A Survey—0
Can Open-Source LLMs Compete with Commercial Models? Exploring the Few-Shot Performance of Current GPT Models in Biomedical TasksCode0
Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach—0
PRAGyan -- Connecting the Dots in Tweets—0
EchoSight: Advancing Visual-Language Models with Wiki Knowledge—0
Evaluating Search Engines and Large Language Models for Answering Health QuestionsCode0
Explainable Biomedical Hypothesis Generation via Retrieval Augmented Generation enabled Large Language Models—0
Optimizing Query Generation for Enhanced Document Retrieval in RAG—0
Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation—0
A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting—0
Show:102550
← PrevPage 70 of 85Next →

No leaderboard results yet.