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 1801–1850 of 2111 papers

TitleStatusHype
RAG vs. GraphRAG: A Systematic Evaluation and Key Insights—0
Examining Long-Context Large Language Models for Environmental Review Document Comprehension—0
RAG Without the Lag: Interactive Debugging for Retrieval-Augmented Generation Pipelines—0
RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models—0
RAGXplain: From Explainable Evaluation to Actionable Guidance of RAG Pipelines—0
RAG-Zeval: Towards Robust and Interpretable Evaluation on RAG Responses through End-to-End Rule-Guided Reasoning—0
Raiders of the Lost Dependency: Fixing Dependency Conflicts in Python using LLMs—0
RAMIE: Retrieval-Augmented Multi-task Information Extraction with Large Language Models on Dietary Supplements—0
RAMO: Retrieval-Augmented Generation for Enhancing MOOCs Recommendations—0
RAM: Towards an Ever-Improving Memory System by Learning from Communications—0
Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains—0
RankLLM: A Python Package for Reranking with LLMs—0
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs—0
RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection—0
RAVEN: Multitask Retrieval Augmented Vision-Language Learning—0
Re2G: Retrieve, Rerank, Generate—0
Reading with Intent—0
Reading with Intent -- Neutralizing Intent—0
NitiBench: A Comprehensive Studies of LLM Frameworks Capabilities for Thai Legal Question AnsweringCode0
Network-informed Prompt Engineering against Organized Astroturf Campaigns under Extreme Class ImbalanceCode0
NeoQA: Evidence-based Question Answering with Generated News EventsCode0
Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language ModelsCode0
CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAGCode0
MuseRAG: Idea Originality Scoring At ScaleCode0
Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation SystemsCode0
Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production ChallengesCode0
Are LLMs effective psychological assessors? Leveraging adaptive RAG for interpretable mental health screening through psychometric practiceCode0
Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-AnsweringCode0
Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical ApplicationsCode0
MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM HallucinationsCode0
SMARTFinRAG: Interactive Modularized Financial RAG BenchmarkCode0
Are Large Language Models Good at Utility Judgments?Code0
Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical StudyCode0
FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial DocumentsCode0
Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented GenerationCode0
SoccerRAG: Multimodal Soccer Information Retrieval via Natural QueriesCode0
AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video UnderstandingCode0
Financial Report Chunking for Effective Retrieval Augmented GenerationCode0
Mitigating Bias in RAG: Controlling the EmbedderCode0
MindScope: Exploring cognitive biases in large language models through Multi-Agent SystemsCode0
A Reality Check on Context Utilisation for Retrieval-Augmented GenerationCode0
RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented GenerationCode0
Better RAG using Relevant Information GainCode0
On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation SystemsCode0
Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation FrameworkCode0
Toward Optimal Search and Retrieval for RAGCode0
Typed-RAG: Type-aware Multi-Aspect Decomposition for Non-Factoid Question AnsweringCode0
Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMsCode0
Micro-Act: Mitigate Knowledge Conflict in Question Answering via Actionable Self-ReasoningCode0
Response Quality Assessment for Retrieval-Augmented Generation via Conditional Conformal FactualityCode0
Show:102550
← PrevPage 37 of 43Next →

No leaderboard results yet.