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 201–225 of 2111 papers

TitleStatusHype
Reranking with Compressed Document Representation—0
HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph DatabasesCode0
Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval—0
Adaptive Plan-Execute Framework for Smart Contract Security Auditing—0
Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign QueriesCode1
Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization—0
RAG/LLM Augmented Switching Driven Polymorphic Metaheuristic Framework—0
SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation—0
Multimodal RAG-driven Anomaly Detection and Classification in Laser Powder Bed Fusion using Large Language Models—0
s3: You Don't Need That Much Data to Train a Search Agent via RLCode4
Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement LearningCode1
MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM HallucinationsCode0
Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering—0
Benchmarking the Myopic Trap: Positional Bias in Information RetrievalCode5
RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture UnderstandingCode0
Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks—0
Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning—0
Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation—0
Know Or Not: a library for evaluating out-of-knowledge base robustnessCode1
AMAQA: A Metadata-based QA Dataset for RAG Systems—0
Effective and Transparent RAG: Adaptive-Reward Reinforcement Learning for Decision TraceabilityCode1
Towards A Generalist Code Embedding Model Based On Massive Data Synthesis—0
Evaluating the Performance of RAG Methods for Conversational AI in the Airport Domain—0
RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection—0
Re-identification of De-identified Documents with Autoregressive Infilling—0
Show:102550
← PrevPage 9 of 85Next →

No leaderboard results yet.