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 376–400 of 2111 papers

TitleStatusHype
Secure Multifaceted-RAG for Enterprise: Hybrid Knowledge Retrieval with Security Filtering—0
RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelines—0
CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models—0
ACoRN: Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models—0
Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Reliable Response Generation in the Wild—0
FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents—0
CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented GenerationCode1
InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning—0
Retrieval-Augmented Generation with Conflicting EvidenceCode1
Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document SummarizationCode0
A Visual RAG Pipeline for Few-Shot Fine-Grained Product Classification—0
A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance JudgmentCode0
On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks—0
ARCeR: an Agentic RAG for the Automated Definition of Cyber Ranges—0
Towards Conversational AI for Human-Machine Collaborative MLOps—0
Enhancing Autonomous Driving Systems with On-Board Deployed Large Language ModelsCode2
Timing Analysis Agent: Autonomous Multi-Corner Multi-Mode (MCMM) Timing Debugging with Timing Debug Relation Graph—0
LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generation—0
ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search—0
Towards Automated Safety Requirements Derivation Using Agent-based RAG—0
ReZero: Enhancing LLM search ability by trying one-more-time—0
Exploring the Role of Knowledge Graph-Based RAG in Japanese Medical Question Answering with Small-Scale LLMs—0
Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance—0
VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents—0
RAKG:Document-level Retrieval Augmented Knowledge Graph ConstructionCode3
Show:102550
← PrevPage 16 of 85Next →

No leaderboard results yet.