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 26–50 of 2111 papers

TitleStatusHype
AI Assistants to Enhance and Exploit the PETSc Knowledge Base—0
MMSearch-R1: Incentivizing LMMs to SearchCode3
CCRS: A Zero-Shot LLM-as-a-Judge Framework for Comprehensive RAG Evaluation—0
Knowledge-Aware Diverse Reranking for Cross-Source Question Answering—0
Memento: Note-Taking for Your Future Self—0
SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models—0
KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language Models—0
Dialogic Pedagogy for Large Language Models: Aligning Conversational AI with Proven Theories of Learning—0
Controlled Retrieval-augmented Context Evaluation for Long-form RAG—0
Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical Tasks—0
QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges—0
Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs—0
RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base—0
T-CPDL: A Temporal Causal Probabilistic Description Logic for Developing Logic-RAG Agent—0
REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing—0
SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification—0
From RAG to Agentic: Validating Islamic-Medicine Responses with LLM Agents—0
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax TreeCode2
Automated Decision-Making on Networks with LLMs through Knowledge-Guided Evolution—0
Lightweight Relevance Grader in RAGCode0
AviationLLM: An LLM-based Knowledge System for Aviation Training—0
RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition—0
AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video UnderstandingCode0
LTRR: Learning To Rank Retrievers for LLMsCode0
Tree-Based Text Retrieval via Hierarchical Clustering in RAGFrameworks: Application on Taiwanese RegulationsCode0
Show:102550
← PrevPage 2 of 85Next →

No leaderboard results yet.