This repository is a curated list of advanced papers on Retrieval Augmented Generation (RAG) in Large Language Models (LLMs). It serves as a valuable resource for researchers and practitioners looking to stay updated on the latest advancements in RAG techniques, applications, and evaluation methods. The primary benefit is providing a centralized, organized collection of cutting-edge research in this rapidly evolving field.

How It Works

The repository categorizes papers and resources related to RAG into distinct areas such as Retrieval-enhanced LLMs, RAG Instruction Tuning, RAG In-Context Learning, RAG Embeddings, RAG Simulators, RAG Search, RAG Long-text and Memory, RAG Evaluation, RAG Optimization, and RAG Applications. This structured approach allows users to easily navigate and find relevant research based on specific RAG sub-topics.

Quick Start & Requirements

This is a curated list, not a software package. No installation or execution is required.

Highlighted Details

• Comprehensive coverage of RAG sub-fields, including specialized areas like RAG Simulators and RAG Long-text and Memory.
• Includes links to papers, GitHub repositories, and models for direct access to research artifacts.
• Features recent workshops and tutorials, offering practical insights and learning opportunities.
• Covers a wide range of RAG applications, from finance to medical question answering.

Maintenance & Community

The repository encourages community contributions via pull requests to update paper information, indicating an active, community-driven maintenance model. Specific contributors or maintainers are not highlighted beyond the authors of the listed papers.

Licensing & Compatibility

The repository itself does not have a specified license. The linked papers and code repositories will have their own respective licenses, which users must adhere to.

Limitations & Caveats

This is a curated list of research papers and does not provide any executable code or models directly. Users must independently access and evaluate the linked resources. The "awesome" nature implies a subjective selection of papers, and completeness is not guaranteed.