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 151–200 of 2111 papers

TitleStatusHype
Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents—0
It's High Time: A Survey of Temporal Information Retrieval and Question Answering—0
KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge TracingCode1
DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients—0
DGRAG: Distributed Graph-based Retrieval-Augmented Generation in Edge-Cloud Systems—0
LLM-Agent-Controller: A Universal Multi-Agent Large Language Model System as a Control Engineer—0
RankLLM: A Python Package for Reranking with LLMsCode0
Hypercube-RAG: Hypercube-Based Retrieval-Augmented Generation for In-domain Scientific Question-AnsweringCode0
Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style—0
POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalCode1
Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarking—0
Vision Meets Language: A RAG-Augmented YOLOv8 Framework for Coffee Disease Diagnosis and Farmer AssistanceCode0
Towards Emotionally Consistent Text-Based Speech Editing: Introducing EmoCorrector and The ECD-TSE DatasetCode0
GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal SynthesisCode1
The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems—0
LLMs for Supply Chain Management—0
Federated Retrieval-Augmented Generation: A Systematic Mapping Study—0
Benchmarking Poisoning Attacks against Retrieval-Augmented Generation—0
Removal of Hallucination on Hallucination: Debate-Augmented RAGCode1
BRIT: Bidirectional Retrieval over Unified Image-Text Graph—0
A Survey of LLM DATACode4
QwenLong-CPRS: Towards -LLMs with Dynamic Context Optimization—0
FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain—0
Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMsCode0
MetaGen Blended RAG: Higher Accuracy for Domain-Specific Q&A Without Fine-TuningCode1
Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps—0
Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty—0
Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval Augmented Generation (RAG)—0
DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes—0
VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering—0
BAGELS: Benchmarking the Automated Generation and Extraction of Limitations from Scholarly Text—0
Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems—0
Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA—0
Continually Self-Improving Language Models for Bariatric Surgery Question--Answering—0
MuseRAG: Idea Originality Scoring At ScaleCode0
R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement LearningCode4
CUB: Benchmarking Context Utilisation Techniques for Language Models—0
HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation—0
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory SynthesisCode4
Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation—0
Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools—0
Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation—0
Ask, Retrieve, Summarize: A Modular Pipeline for Scientific Literature SummarizationCode0
Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph WalksCode0
Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks—0
After Retrieval, Before Generation: Enhancing the Trustworthiness of Large Language Models in RAG—0
InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation—0
BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law—0
Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains—0
Reranking with Compressed Document Representation—0
Show:102550
← PrevPage 4 of 43Next →

No leaderboard results yet.