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 251–300 of 2111 papers

TitleStatusHype
LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff TableCode1
TracLLM: A Generic Framework for Attributing Long Context LLMsCode1
PAKTON: A Multi-Agent Framework for Question Answering in Long Legal AgreementsCode1
Sentinel: Attention Probing of Proxy Models for LLM Context Compression with an Understanding PerspectiveCode1
NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question AnsweringCode1
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement LearningCode1
Benchmarking Multimodal Knowledge Conflict for Large Multimodal ModelsCode1
KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge TracingCode1
POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalCode1
GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal SynthesisCode1
Removal of Hallucination on Hallucination: Debate-Augmented RAGCode1
MetaGen Blended RAG: Higher Accuracy for Domain-Specific Q&A Without Fine-TuningCode1
Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign QueriesCode1
Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement LearningCode1
Effective and Transparent RAG: Adaptive-Reward Reinforcement Learning for Decision TraceabilityCode1
Know Or Not: a library for evaluating out-of-knowledge base robustnessCode1
Neuro-Symbolic Query CompilerCode1
ELITE: Embedding-Less retrieval with Iterative Text ExplorationCode1
mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge GraphsCode1
RAGSynth: Synthetic Data for Robust and Faithful RAG Component OptimizationCode1
Finetune-RAG: Fine-Tuning Language Models to Resist Hallucination in Retrieval-Augmented GenerationCode1
Hierarchical Document Refinement for Long-context Retrieval-augmented GenerationCode1
Chronocept: Instilling a Sense of Time in MachinesCode1
Efficient and Reproducible Biomedical Question Answering using Retrieval Augmented GenerationCode1
MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAGCode1
KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text ClassificationCode1
Benchmarking LLM Faithfulness in RAG with Evolving LeaderboardsCode1
Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-PracticingCode1
LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household RoboticsCode1
TreeHop: Generate and Filter Next Query Embeddings Efficiently for Multi-hop Question AnsweringCode1
Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented GenerationCode1
A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and AdaptationCode1
AlignRAG: Leveraging Critique Learning for Evidence-Sensitive Retrieval-Augmented ReasoningCode1
CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented GenerationCode1
Retrieval-Augmented Generation with Conflicting EvidenceCode1
Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End SystemCode1
HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive ModulesCode1
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight DiscoveryCode1
MRD-RAG: Enhancing Medical Diagnosis with Multi-Round Retrieval-Augmented GenerationCode1
Retrieval Augmented Generation with Collaborative Filtering for Personalized Text GenerationCode1
Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM CollaborationCode1
Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-GenerationCode1
WikiVideo: Article Generation from Multiple VideosCode1
InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation SystemCode1
Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense RetrievalCode1
ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented GenerationCode1
Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language ModelsCode1
Tuning LLMs by RAG Principles: Towards LLM-native MemoryCode1
Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation SystemsCode1
JuDGE: Benchmarking Judgment Document Generation for Chinese Legal SystemCode1
Show:102550
← PrevPage 6 of 43Next →

No leaderboard results yet.