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 1001–1050 of 2111 papers

TitleStatusHype
EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented GenerationCode1
RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement—0
OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial DomainCode2
PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation—0
Adaptations of AI models for querying the LandMatrix database in natural languageCode0
Advanced ingestion process powered by LLM parsing for RAG system—0
Unanswerability Evaluation for Retrieval Augmented Generation—0
RAG Playground: A Framework for Systematic Evaluation of Retrieval Strategies and Prompt Engineering in RAG SystemsCode1
BioRAGent: A Retrieval-Augmented Generation System for Showcasing Generative Query Expansion and Domain-Specific Search for Scientific Q&ACode0
LogBabylon: A Unified Framework for Cross-Log File Integration and Analysis—0
Let your LLM generate a few tokens and you will reduce the need for retrieval—0
Attention with Dependency Parsing Augmentation for Fine-Grained Attribution—0
Agentic AI-Driven Technical Troubleshooting for Enterprise Systems: A Novel Weighted Retrieval-Augmented Generation Paradigm—0
RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within GenerationCode2
One-Shot Multilingual Font Generation Via ViT—0
RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving with Vision-Language Models—0
Streamlining Systematic Reviews: A Novel Application of Large Language Models—0
Accelerating Retrieval-Augmented Generation—0
Inference Scaling for Bridging Retrieval and Augmented Generation—0
VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation—0
SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report GenerationCode1
RAGServe: Fast Quality-Aware RAG Systems with Configuration Adaptation—0
Evidence Contextualization and Counterfactual Attribution for Conversational QA over Heterogeneous Data with RAG Systems—0
CaLoRAify: Calorie Estimation with Visual-Text Pairing and LoRA-Driven Visual Language ModelsCode1
VLR-Bench: Multilingual Benchmark Dataset for Vision-Language Retrieval Augmented Generation—0
OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models—0
Assessing the Robustness of Retrieval-Augmented Generation Systems in K-12 Educational Question Answering with Knowledge Discrepancies—0
Context Canvas: Enhancing Text-to-Image Diffusion Models with Knowledge Graph-Based RAG—0
Leveraging Graph-RAG and Prompt Engineering to Enhance LLM-Based Automated Requirement Traceability and Compliance Checks—0
Federated In-Context LLM Agent Learning—0
Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation—0
Ontology-Aware RAG for Improved Question-Answering in Cybersecurity Education—0
RAG-based Question Answering over Heterogeneous Data and Text—0
Granite GuardianCode2
OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive AnnotationsCode5
Privacy-Preserving Customer Support: A Framework for Secure and Scalable Interactions—0
Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge GraphsCode1
LLM as HPC Expert: Extending RAG Architecture for HPC Data—0
Efficient VoIP Communications through LLM-based Real-Time Speech Reconstruction and Call Prioritization for Emergency Services—0
SiReRAG: Indexing Similar and Related Information for Multihop Reasoning—0
Retrieving Semantics from the Deep: an RAG Solution for Gesture SynthesisCode2
Mixture-of-PageRanks: Replacing Long-Context with Real-Time, Sparse GraphRAG—0
A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data—0
Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design—0
DECO: Life-Cycle Management of Enterprise-Grade Copilots—0
SLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question Answering—0
GEE-OPs: An Operator Knowledge Base for Geospatial Code Generation on the Google Earth Engine Platform Powered by Large Language Models—0
KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language ModelsCode1
TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG—0
100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo—0
Show:102550
← PrevPage 21 of 43Next →

No leaderboard results yet.