https://github.com/wujwyi/pa-rag
공식 코드PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering
NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering
Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation
Revolutionizing Database Q&A with Large Language Models: Comprehensive Benchmark and Evaluation
List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation
MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search
AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations
Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems
R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation
RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
MRD-RAG: Enhancing Medical Diagnosis with Multi-Round Retrieval-Augmented Generation
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries
You Only Use Reactive Attention Slice For Long Context Retrieval
Improving Medical Multi-modal Contrastive Learning with Expert Annotations
Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation
RAGPPI: RAG Benchmark for Protein-Protein Interactions in Drug Discovery
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contexts
PoisonArena: Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.