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 1976–2000 of 2111 papers

TitleStatusHype
PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering—0
In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs MissCode4
RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language ModelCode2
Generative AI in the Construction Industry: A State-of-the-art Analysis—0
Grounding Language Model with Chunking-Free In-Context Retrieval—0
Generative Representational Instruction TuningCode4
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question AnsweringCode4
T-RAG: Lessons from the LLM Trenches—0
PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language ModelsCode3
A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and AdaptationCode1
CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity KnowledgeCode2
Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models—0
REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language ModelsCode0
Enhancing Retrieval Processes for Language Generation with Augmented Queries—0
DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton—0
Enhancing textual textbook question answering with large language models and retrieval augmented generationCode0
Financial Report Chunking for Effective Retrieval Augmented GenerationCode0
Multi-Lingual Malaysian Embedding: Leveraging Large Language Models for Semantic Representations—0
C-RAG: Certified Generation Risks for Retrieval-Augmented Language ModelsCode1
Improving Assessment of Tutoring Practices using Retrieval-Augmented Generation—0
How well do LLMs cite relevant medical references? An evaluation framework and analysesCode1
LitLLM: A Toolkit for Scientific Literature ReviewCode2
Retrieval Augmented End-to-End Spoken Dialog Models—0
CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks—0
HiQA: A Hierarchical Contextual Augmentation RAG for Multi-Documents QA—0
Show:102550
← PrevPage 80 of 85Next →

No leaderboard results yet.