awesome-papers-for-rag

A curated list of resources dedicated to retrieval-augmented generation (RAG).

The retrieval-augmented generation (RAG) is to combine the merits of retrieval system and llm to generation high-quality answers for users.

The Framework for RAG System

Typically, the rag system consists of a set of modules, where each task are described as follows:

Sub-Tasks	Input	Output
query understanding	question	search queries
document retrieval	question/queries	documents
evidence extraction	questions+documents	contexts
answer generation	question+contexts	answer
result enhancement	question+answer+contexts	answer

Healthcheck

pip3 install -r requirements.txt
python3 healthcheck.py

Surveys for RAG

• The Organization column only record the organization of the first author.

Date	Title	Organization	Code
2024/02/29	Retrieval-Augmented Generation for AI-Generated Content: A Survey	Peking University	Code
2024/01/03	Retrieval-Augmented Generation for Large Language Models: A Survey	Tongji University	Code
2024/01/03	A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models	Islamic University of Technology	No
2023/12/07	Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications	Harbin Institute of Technology	No
2023/09/19	The Rise and Potential of Large Language Model Based Agents: A Survey	Fudan NLP Group	Code
2023/08/14	Large Language Models for Information Retrieval: A Survey	Renmin University	Code
2022/02/02	A Survey on Retrieval-Augmented Text Generation	Nara Institute of Science and Techonology	No

Systems for RAG

• The Organization column only record the organization of the first author.

Date	Title	Organization	Code
2023/11/22	FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation	Google	Code
2023/11/08	PDFTriage: Question Answering over Long, Structured Documents	Stanford	Code
2023/10/27	WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia	Stanford	Code
2023/10/27	LeanDojo: Theorem Proving with Retrieval-Augmented Language Models	Caltech	Code
2023/06/13	WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences	Tsinghua University	Code
2023/05/23	WebCPM: Interactive Web Search for Chinese Long-form Question Answering	Tsinghua University	Code
2022/06/01	WebGPT: Browser-assisted question-answering with human feedback	Open AI	No

Evaluations for RAG

• The Organization column only record the organization of the first author.

Date	Title	Organization	Code
2024/05/22	FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research	Renmin University of China	Code
2024/05/13	Evaluation of Retrieval-Augmented Generation: A Survey	Tencent	Code
2024/04/21	Evaluating Retrieval Quality in Retrieval-Augmented Generation	UMASS	No
2024/04/08	FaaF: Facts as a Function for the evaluation of generated text	IMMO Capital	Code
2024/02/19	CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models	University of Science and Technology of China	Code
2024/1/30	RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture	Microsoft	No
2024/1/11	Seven Failure Points When Engineering a Retrieval Augmented Generation System	Applied Artificial Intelligence Institute	No
2023/12/20	Benchmarking Large Language Models in Retrieval-Augmented Generation	Chinese Information Processing Laboratory	Code
2023/11/16	ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems	Stanford	Code
2023/11/14	RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge	Peking University	No
2023/10/31	Enabling Large Language Models to Generate Text with Citations	Princeton University	Code
2023/09/26	RAGAS: Automated Evaluation of Retrieval Augmented Generation	Exploding Gradients	Code
2021/08/05	TruLens:Evaluation and Tracking for LLM Experiments	TruEra	Code