Tongji-KGLLM/RAG-Survey
A comprehensive survey repository on Retrieval-Augmented Generation (RAG) for Large Language Models by Tongji University researchers.
Velocity · 7d
+2.4
★ / day
Trend
→steady
star history
The repository hosts the RAG Survey paper (arXiv:2312.10997) covering paradigms, augmentation strategies, evaluation methods, and future prospects of RAG systems. It includes an OpenRAG Base knowledge base consolidating RAG research and knowledge. The project provides resources including slides and structured documentation on when to use RAG versus fine-tuning for LLM applications.