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 601–625 of 2111 papers

TitleStatusHype
TPU-Gen: LLM-Driven Custom Tensor Processing Unit Generator—0
ORANSight-2.0: Foundational LLMs for O-RAN—0
FinTMMBench: Benchmarking Temporal-Aware Multi-Modal RAG in Finance—0
Automatic Teaching Platform on Vision Language Retrieval Augmented Generation—0
TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster—0
Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence—0
Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning—0
In-depth Analysis of Graph-based RAG in a Unified Framework—0
LeRAAT: LLM-Enabled Real-Time Aviation Advisory ToolCode0
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning—0
Optimizing open-domain question answering with graph-based retrieval augmented generation—0
OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing—0
RAAD-LLM: Adaptive Anomaly Detection Using LLMs and RAG Integration—0
PennyLang: Pioneering LLM-Based Quantum Code Generation with a Novel PennyLane-Centric Dataset—0
Wikipedia in the Era of LLMs: Evolution and RisksCode0
HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation—0
SAGE: A Framework of Precise Retrieval for RAG—0
SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph—0
Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAGCode2
SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity ReductionCode1
ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources—0
Optimizing Multi-Hop Document Retrieval Through Intermediate Representations—0
Towards Efficient Educational Chatbots: Benchmarking RAG Frameworks—0
GPIoT: Tailoring Small Language Models for IoT Program Synthesis and DevelopmentCode1
U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-HaystackCode0
Show:102550
← PrevPage 25 of 85Next →

No leaderboard results yet.