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 1901–1950 of 2111 papers

TitleStatusHype
ARAGOG: Advanced RAG Output GradingCode2
RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation—0
Observations on Building RAG Systems for Technical Documents—0
Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs—0
Towards a Robust Retrieval-Based Summarization SystemCode0
Are Large Language Models Good at Utility Judgments?Code0
MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering—0
FACTOID: FACtual enTailment fOr hallucInation Detection—0
CPR: Retrieval Augmented Generation for Copyright Protection—0
Boosting Conversational Question Answering with Fine-Grained Retrieval-Augmentation and Self-Check—0
Evaluation of Semantic Search and its Role in Retrieved-Augmented-Generation (RAG) for Arabic Language—0
Generation of Asset Administration Shell with Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0Code1
LexDrafter: Terminology Drafting for Legislative Documents using Retrieval Augmented GenerationCode1
Fine Tuning LLM for Enterprise: Practical Guidelines and Recommendations—0
Improving Retrieval for RAG based Question Answering Models on Financial Documents—0
Towards a RAG-based Summarization Agent for the Electron-Ion ColliderCode0
General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing—0
Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based RetrieversCode2
Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question ComplexityCode3
FIT-RAG: Black-Box RAG with Factual Information and Token Reduction—0
AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain FrameworkCode3
Dynamic Contexts for Generating Suggestion Questions in RAG Based Conversational Systems—0
JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-TuningCode1
Improving Medical Multi-modal Contrastive Learning with Expert AnnotationsCode0
Repoformer: Selective Retrieval for Repository-Level Code Completion—0
DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language ModelsCode2
S3LLM: Large-Scale Scientific Software Understanding with LLMs using Source, Metadata, and DocumentCode1
RAFT: Adapting Language Model to Domain Specific RAGCode0
Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-BasesCode1
Exploring the Capabilities and Limitations of Large Language Models in the Electric Energy Sector—0
Retrieval augmented text-to-SQL generation for epidemiological question answering using electronic health recordsCode1
RAGGED: Towards Informed Design of Retrieval Augmented Generation SystemsCode2
From human experts to machines: An LLM supported approach to ontology and knowledge graph constructionCode3
Investigating the performance of Retrieval-Augmented Generation and fine-tuning for the development of AI-driven knowledge-based systemsCode0
AesopAgent: Agent-driven Evolutionary System on Story-to-Video Production—0
Development of a Reliable and Accessible Caregiving Language Model (CaLM)—0
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-FeedbackCode2
PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design—0
HaluEval-Wild: Evaluating Hallucinations of Language Models in the WildCode0
Federated Recommendation via Hybrid Retrieval Augmented GenerationCode1
Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection AttacksCode1
FaaF: Facts as a Function for the evaluation of generated textCode0
Fine Tuning vs. Retrieval Augmented Generation for Less Popular KnowledgeCode0
Towards Comprehensive Vietnamese Retrieval-Augmented Generation and Large Language Models—0
RAGged Edges: The Double-Edged Sword of Retrieval-Augmented Chatbots—0
DFIN-SQL: Integrating Focused Schema with DIN-SQL for Superior Accuracy in Large-Scale Databases—0
Crafting Knowledge: Exploring the Creative Mechanisms of Chat-Based Search Engines—0
Retrieval-Augmented Generation for AI-Generated Content: A SurveyCode5
RNNs are not Transformers (Yet): The Key Bottleneck on In-context RetrievalCode1
WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World ScenarioCode1
Show:102550
← PrevPage 39 of 43Next →

No leaderboard results yet.