Awesome RAG 📄🔍
A curated list of awesome resources for RAG (Retrieval Augmentation Generation) exploration.
Table of Contents
Papers
Retrieval
-
RAG: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks - An information retrieval augmented generation model that can be used for various knowledge-intensive NLP tasks. (Lewis, Patrick, et al. 2020)
-
RA-DIT: Retrieval-Augmented Dual Instruction Tuning (RA-DIT) - Improve the performance of retrieval-augmented generation models by fine-tuning the retrieval and generation components jointly. (Khattar, Dheeraj, et al. 2021)
-
CRAG - Corrective Retrieval Augmented Generation Llama Pack - Enhance the robustness of language model generation by evaluating and augmenting the relevance of retrieved documents through a an evaluator and large-scale web searches. (Shi-Qi Yan, Jia-Chen Gu, et al. 2024)
-
Dense x Retrieval: What Retrieval Grnaularity Should We Use? - Improve dense retrieval by using a more fine-grained retrieval granularity as known as Propositions. (Tong Chen, et al. 2023)
-
In-Context Learning for Extreme Multi-Label Classification - A retrieval-augmented generation model that can be used for extreme multi-label classification. (Karel, et al. 2021)
-
Self-Discover: Large Language Models Self-Compose Reasoning Structures - A retrieval-augmented generation model that can be used for self-composing reasoning structures. (Pei, et al. 2021)
-
SELF-RAG: LEARNING TO RETRIEVE, GENERATE, AND CRITIQUE THROUGH SELF-REFLECTION - A retrieval-augmented generation model that can be used for self-reflection. (Akari, et al. 2023)
-
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding - A retrieval-augmented generation model that can be used for table understanding. (Zilong, et al. 2024)
-
InstructRetro: Instruction Tuning Post Retrieval-Augmented Pretraining - A Large Language Model pretrained with retrieval before instruction tuning (Wei Ping, et al. 2023)
-
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval - An approach to enhance RAG by creating a summary tree from text chunks, providing deeper insights and overcoming the limitations of short, contiguous text retrieval. (Sarthi, Parth, et al. 2024)
-
HiQA: A Hierarchical Contextual Augmentation RAG for Massive Documents QA - An advanced multi-document question-answering framework that integrates cascading metadata and a multi-route retrieval mechanism, enhancing the accuracy of RAG pipeline. (Chen, Xinyue, et al. 2024)
-
ActiveRAG: Revealing the Treasures of Knowledge via Active Learning - Enhances RAG by active learning to deepen LLMs' understanding of external knowledge through innovative Knowledge Construction and Cognitive Nexus mechanisms. (Xu, Zhipeng, et al. 2024)
RAG vs Finetuning
- RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture - RAG vs Fine-tuning case study on agriculture domain datasets. (Gupta, Aman, et al. 2024)
RAG With Knowledge Graphs
Evaluation
Agents/Tools
Survey Papers
Contributing
Interested in contributing? Please read the contribution guidelines first.