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 51–100 of 2111 papers

TitleStatusHype
Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token SequencesCode3
SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative RefinementCode1
FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented GenerationCode3
RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning—0
Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation—0
Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs—0
Large Language Model-Powered Conversational Agent Delivering Problem-Solving Therapy (PST) for Family Caregivers: Enhancing Empathy and Therapeutic Alliance Using In-Context Learning—0
Dr. GPT Will See You Now, but Should It? Exploring the Benefits and Harms of Large Language Models in Medical Diagnosis using Crowdsourced Clinical Cases—0
LLM Embedding-based Attribution (LEA): Quantifying Source Contributions to Generative Model's Response for Vulnerability AnalysisCode0
Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry ChallengesCode0
Constructing and Evaluating Declarative RAG Pipelines in PyTerrierCode1
Augmenting Large Language Models with Static Code Analysis for Automated Code Quality Improvements—0
CIIR@LiveRAG 2025: Optimizing Multi-Agent Retrieval Augmented Generation through Self-TrainingCode0
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document ReasoningCode2
Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question AnsweringCode0
Bridging the Gap Between Open-Source and Proprietary LLMs in Table QACode0
XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented GenerationCode0
Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service EnvironmentCode0
FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation SystemsCode2
FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented GenerationCode1
DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMsCode1
Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive-k—0
CC-RAG: Structured Multi-Hop Reasoning via Theme-Based Causal Graphs—0
Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning—0
LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based RankingCode0
SceneRAG: Scene-level Retrieval-Augmented Generation for Video Understanding—0
SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from DesignCode1
Swiss Parliaments Corpus Re-Imagined (SPC_R): Enhanced Transcription with RAG-based Correction and Predicted BLEU—0
Hierarchical Lexical Graph for Enhanced Multi-Hop RetrievalCode3
LEANN: A Low-Storage Vector Index—0
Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles—0
AR-RAG: Autoregressive Retrieval Augmentation for Image GenerationCode0
BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions—0
Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation SystemsCode1
Small Models, Big Support: A Local LLM Framework for Teacher-Centric Content Creation and Assessment using RAG and CAG—0
When to use Graphs in RAG: A Comprehensive Analysis for Graph Retrieval-Augmented GenerationCode3
Dynamic Context Tuning for Retrieval-Augmented Generation: Enhancing Multi-Turn Planning and Tool Adaptation—0
Micro-Act: Mitigate Knowledge Conflict in Question Answering via Actionable Self-ReasoningCode0
Mathematical Reasoning for Unmanned Aerial Vehicles: A RAG-Based Approach for Complex Arithmetic ReasoningCode0
ECoRAG: Evidentiality-guided Compression for Long Context RAGCode1
Knowledgeable-r1: Policy Optimization for Knowledge Exploration in Retrieval-Augmented GenerationCode0
LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff TableCode1
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems—0
On Automating Security Policies with Contemporary LLMs—0
R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement LearningCode0
GEM: Empowering LLM for both Embedding Generation and Language Understanding—0
TracLLM: A Generic Framework for Attributing Long Context LLMsCode1
Through the Stealth Lens: Rethinking Attacks and Defenses in RAGCode0
Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systems—0
CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG—0
Show:102550
← PrevPage 2 of 43Next →

No leaderboard results yet.