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 526–550 of 2111 papers

TitleStatusHype
AI Approaches to Qualitative and Quantitative News Analytics on NATO Unity—0
Towards Efficient Educational Chatbots: Benchmarking RAG Frameworks—0
CoRAG: Collaborative Retrieval-Augmented Generation—0
CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation—0
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges—0
Conversational Text Extraction with Large Language Models Using Retrieval-Augmented Systems—0
How Does Knowledge Selection Help Retrieval Augmented Generation?—0
A Comparison of LLM Finetuning Methods & Evaluation Metrics with Travel Chatbot Use Case—0
Conversation AI Dialog for Medicare powered by Finetuning and Retrieval Augmented Generation—0
Control Token with Dense Passage Retrieval—0
A Systematic Evaluation of LLM Strategies for Mental Health Text Analysis: Fine-tuning vs. Prompt Engineering vs. RAG—0
ControlNET: A Firewall for RAG-based LLM System—0
A Survey on Retrieval-Augmented Text Generation for Large Language Models—0
A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning—0
Recording First-person Experiences to Build a New Type of Foundation Model—0
Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations—0
Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation—0
Controlled Retrieval-augmented Context Evaluation for Long-form RAG—0
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models—0
ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation—0
Contrato360 2.0: A Document and Database-Driven Question-Answer System using Large Language Models and Agents—0
A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation—0
A Survey on Knowledge-Oriented Retrieval-Augmented Generation—0
Continually Self-Improving Language Models for Bariatric Surgery Question--Answering—0
A Comparative Study of PDF Parsing Tools Across Diverse Document Categories—0
Show:102550
← PrevPage 22 of 85Next →

No leaderboard results yet.