Retrieval-Augmented Generation Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Core papers on augmenting language models with retrieval — from the original RAG to FiD, Atlas, and modern retrieval-augmented pretraining.

Retrieval-Augmented Generation: 10 key papers

1. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
   Lewis et al. arXiv 2020.
2. Dense Passage Retrieval for Open-Domain Question Answering
   Karpukhin et al. arXiv 2020.
3. REALM: Retrieval-Augmented Language Model Pre-Training
   Guu et al. arXiv 2020.
4. Improving language models by retrieving from trillions of tokens
   Borgeaud et al. arXiv 2021.
5. Atlas: Few-shot Learning with Retrieval Augmented Language Models
   Izacard et al. arXiv 2022.
6. Generalization through Memorization: Nearest Neighbor Language Models
   Khandelwal et al. arXiv 2019.
7. Active Retrieval Augmented Generation
   Jiang et al. arXiv 2023.
8. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
   Asai et al. arXiv 2023.
9. Retrieval-Augmented Generation for Large Language Models: A Survey
   Gao et al. arXiv 2023.
10. Precise Zero-Shot Dense Retrieval without Relevance Labels
    Gao et al. arXiv 2022.

Related reading lists

• Formal Verification & Neural Theorem Proving
• Code Generation & Program Synthesis with RL
• Vision-Language Models & Multimodal Learning
• Long-Context & Memory Transformers
• Instruction Following & Finetuning
• Curriculum Learning & Teacher-Student
• Few-Shot RL & Meta-Learning
• Adaptive Sensing and Active Learning