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 301–350 of 2111 papers

TitleStatusHype
An Open-Source Dual-Loss Embedding Model for Semantic Retrieval in Higher Education—0
Fine-Tuning Large Language Models and Evaluating Retrieval Methods for Improved Question Answering on Building Codes—0
Osiris: A Lightweight Open-Source Hallucination Detection System—0
Retrieval Augmented Generation Evaluation for Health Documents—0
HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights—0
A Proposal for Evaluating the Operational Risk for ChatBots based on Large Language Models—0
The Aloe Family Recipe for Open and Specialized Healthcare LLMs—0
LLM-Independent Adaptive RAG: Let the Question Speak for Itself—0
Benchmarking LLM Faithfulness in RAG with Evolving LeaderboardsCode1
A Reasoning-Focused Legal Retrieval Benchmark—0
RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation—0
An Analysis of Hyper-Parameter Optimization Methods for Retrieval Augmented Generation—0
Capability-Driven Skill Generation with LLMs: A RAG-Based Approach for Reusing Existing Libraries and Interfaces—0
Lightweight Clinical Decision Support System using QLoRA-Fine-Tuned LLMs and Retrieval-Augmented Generation—0
Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language ModelsCode3
SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration—0
Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition—0
SafeMate: A Modular RAG-Based Agent for Context-Aware Emergency Guidance—0
Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-PracticingCode1
Incorporating Legal Structure in Retrieval-Augmented Generation: A Case Study on Copyright Fair UseCode0
Real-time Spatial Retrieval Augmented Generation for Urban Environments—0
A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking—0
Retrieval-augmented in-context learning for multimodal large language models in disease classification—0
Facilitating Video Story Interaction with Multi-Agent Collaborative System—0
Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies, Datasets, and Clinical Applications—0
Document Retrieval Augmented Fine-Tuning (DRAFT) for safety-critical software assessments—0
CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Code—0
Enhancing tutoring systems by leveraging tailored promptings and domain knowledge with Large Language Models—0
Harnessing Structured Knowledge: A Concept Map-Based Approach for High-Quality Multiple Choice Question Generation with Effective DistractorsCode0
Patchwork: A Unified Framework for RAG Serving—0
EnronQA: Towards Personalized RAG over Private Documents—0
HalluMix: A Task-Agnostic, Multi-Domain Benchmark for Real-World Hallucination Detection—0
Empowering Agentic Video Analytics Systems with Video Language Models—0
A Multi-Granularity Retrieval Framework for Visually-Rich Documents—0
LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household RoboticsCode1
Homa at SemEval-2025 Task 5: Aligning Librarian Records with OntoAligner for Subject Tagging—0
Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QACode0
Optimization of embeddings storage for RAG systems using quantization and dimensionality reduction techniques—0
Traceback of Poisoning Attacks to Retrieval-Augmented Generation—0
ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement—0
Information Retrieval in the Age of Generative AI: The RGB ModelCode0
Detecting Manipulated Contents Using Knowledge-Grounded InferenceCode0
Graph RAG for Legal Norms: A Hierarchical and Temporal Approach—0
ReasonIR: Training Retrievers for Reasoning TasksCode3
AKIBoards: A Structure-Following Multiagent System for Predicting Acute Kidney Injury—0
CBM-RAG: Demonstrating Enhanced Interpretability in Radiology Report Generation with Multi-Agent RAG and Concept Bottleneck ModelsCode0
UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and GranularitiesCode2
Mem0: Building Production-Ready AI Agents with Scalable Long-Term MemoryCode16
Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented GenerationCode0
Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets—0
Show:102550
← PrevPage 7 of 43Next →

No leaderboard results yet.