Paper Reading–Awesome RAG

Survey

2025

2024

• Retrieval - Augmented Generation for AI - Generated Content: A Survey

  2024 Paper arXiv

  Paper Reading 13 RAG- AIGC survey — 英飞

• Retrieval-Augmented Generation for Large Language Models: A Survey

  None semanticscholar Paper

  Paper Reading 7 LLM-RAG(Retrieval-Augmented Generation)-survey — 英飞

2023

• Large Language Models for Information Retrieval: A Survey

  2023 Paper arXiv

  Paper Reading 8 LLM-IR(Information Retrieval) — 英飞

RAG model

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

  2020 semanticscholar Paper arXiv

Query-based RAG

• REALM: Retrieval-Augmented Language Model Pre-Training

  2020 semanticscholar Paper arXiv

Latent Representation-based RAG

• RETRO Improving Language Models by Retrieving from Trillions of Tokens

None semanticscholar Paper

Logit-based RAG

• GENERALIZATION THROUGH MEMORIZATION: NEAREST NEIGHBOR LANGUAGE MODELS

  kNN-LMs 2019 semanticscholar Paper arXiv

Speculative RAG

• Copy Is All You Need

  coG 2023 semanticscholar Paper arXiv

  International Conference on Learning Representations

• RETRIEVAL IS ACCURATE GENERATION

  2024 semanticscholar Paper arXiv International Conference on Learning Representations

RAG enhancement

Input Enhancemnt

Query Transformation:

• Query2doc: Query Expansion with Large Language Models

  14 March 2023 Conference on Empirical Methods in Natural Language Processing

  semanticscholar Paper arXiv

• Precise Zero-Shot Dense Retrieval without Relevance Labels

  semanticscholar Paper

  HyDE 20 December 2022 Annual Meeting of the Association for Computational Linguistics

• CHAIN-OF-VERIFICATION REDUCES HALLUCINATION IN LARGE LANGUAGE MODELS

  semanticscholar Paper arXiv

  CoVe 20 September 2023 Annual Meeting of the Association for Computational Linguistics

Data Augment

• Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory

  semanticscholar Paper arXiv

  3 May 2023 Neural Information Processing Systems

• PROMPTAGATOR : FEW-SHOT DENSE RETRIEVAL FROM 8 EXAMPLES

  semanticscholar Paper

  2022 International Conference on Learning Representations

Retrieval Enhancement

Retrieval Finetuning

• L2R: Lifelong Learning for First-stage Retrieval with Backward-Compatible Representations

  2023 semanticscholar Paper

  Paper Reading 9 LLM- First-stage Retrieval L2R — 英飞

• Continual Learning of Long Topic Sequences in Neural Information Retrieval

  2022 semanticscholar Paper arXiv

  Paper Reading 10 LLM- Continual Learning of Long Topic Sequences in Neural Information Retrieval — 英飞

• REPLUG: Retrieval-Augmented Black-Box Language Models

  semanticscholar Paper

  2023 North American Chapter of the Association for Computational Linguistics

• Augmented Large Language Models with Parametric Knowledge Guiding

  semanticscholar Paper

  PKG 2023 arXiv.org

• Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data

  semanticscholar Paper

  ​

Re-ranking

• Studying Catastrophic Forgetting in Neural Ranking Models

  2021 semanticscholar Paper arXiv

  Paper Reading 11 LLM- Studying Catastrophic Forgetting in Neural Ranking Models — 英飞

• Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

  semanticscholar Paper

Recursive Retrieval

• Query Rewriting for Retrieval-Augmented Large Language Models

  semanticscholar Paper

• Bridging the Preference Gap between Retrievers and LLMs

  semanticscholar Paper

Hybrid Retrieval

• ISEEQ: Information Seeking Question Generation Using Dynamic Meta-Information Retrieval and Knowledge Graphs

  semanticscholar Paper

  2021 AAAI Conference on Artificial Intelligence

RAG application in Image

Image Generation

• KNN-Diffusion: Image Generation via Large-Scale Retrieval

  semanticscholar Paper

• RE-IMAGEN: RETRIEVAL-AUGMENTED TEXT-TO-IMAGE GENERATOR

  semanticscholar Paper

RAG application in Knowledge

• G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering

  semanticscholar Paper

Evaluation

Benchmarking Large Language Models in Retrieval-Augmented Generation

semanticscholar Paper