Retrieval-Augmented Generation

Grounding language models in retrieved, non-parametric memory; retrieve-then-generate systems.

A topic in the Science corpus, drawn from 180 papers.

Trusted voices in Retrieval-Augmented Generation

Ordered by the trust Retrieval-Augmented Generation's own network concentrates on each researcher, most first.

  1. Jason Aaron Edward Weston — trusted by 141 researchers here
  2. Sumit Chopra — trusted by 133 researchers here
  3. Antoine Bordes — trusted by 133 researchers here
  4. Gautier Izacard — trusted by 120 researchers here
  5. Edouard Grave — trusted by 120 researchers here
  6. Patrick Lewis — trusted by 73 researchers here
  7. Wen-tau Yih — trusted by 61 researchers here
  8. Vladimir Karpukhin — trusted by 53 researchers here
  9. Panupong Pasupat — trusted by 51 researchers here
  10. Kelvin Guu — trusted by 51 researchers here
  11. Ming-Wei Chang — trusted by 48 researchers here
  12. Zora Tung — trusted by 43 researchers here

Most-cited papers in Retrieval-Augmented Generation

Ordered by the recorded citation count from the source corpus; a citation is not an endorsement.

  1. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (2020, Neural Information Processing Systems) — 16,110 citations
  2. Dense Passage Retrieval for Open-Domain Question Answering (2020, Conference on Empirical Methods in Natural Language Processing) — 6,334 citations
  3. Retrieval-Augmented Generation for Large Language Models: A Survey (2023) — 3,697 citations
  4. REALM: Retrieval-Augmented Language Model Pre-Training (2020, International Conference on Machine Learning) — 3,207 citations
  5. WebGPT: Browser-assisted question-answering with human feedback (2021) — 1,953 citations
  6. Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering (2020, Conference of the European Chapter of the Association for Computational Linguistics) — 1,909 citations
  7. Memory Networks (2014) — 1,867 citations
  8. Improving language models by retrieving from trillions of tokens (2021) — 1,785 citations
  9. When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories (2022) — 1,304 citations
  10. Few-shot Learning with Retrieval Augmented Language Models (2022, Journal of machine learning research) — 1,295 citations
  11. Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions (2022) — 1,143 citations
  12. Retrieval Augmentation Reduces Hallucination in Conversation (2021) — 1,126 citations
  13. REPLUG: Retrieval-Augmented Black-Box Language Models (2023) — 1,051 citations
  14. KILT: a Benchmark for Knowledge Intensive Language Tasks (2020) — 820 citations
  15. A Knowledge-Grounded Neural Conversation Model (2017) — 591 citations
  16. Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback (2023) — 530 citations
  17. RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation (2023) — 516 citations
  18. LeanDojo: Theorem Proving with Retrieval-Augmented Language Models (2023) — 514 citations
  19. PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text (2019) — 464 citations
  20. Transformer Memory as a Differentiable Search Index (2022) — 444 citations
  21. Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation (2018) — 436 citations
  22. Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning (2020) — 410 citations
  23. Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval (2021) — 395 citations
  24. Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge from External Sources (2015) — 392 citations
  25. TAPEX: Table Pre-training via Learning a Neural SQL Executor (2021) — 368 citations
  26. Generation-Augmented Retrieval for Open-Domain Question Answering (2020) — 323 citations
  27. Condenser: a Pre-training Architecture for Dense Retrieval (2021) — 308 citations
  28. MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (2024) — 304 citations
  29. Evaluation of Retrieval-Augmented Generation: A Survey (2024) — 292 citations
  30. Re-Imagen: Retrieval-Augmented Text-to-Image Generator (2022) — 260 citations
  31. Fine-grained Fact Verification with Kernel Graph Attention Network (2019) — 254 citations
  32. Explaining Answers with Entailment Trees (2021) — 232 citations
  33. Rethinking with Retrieval: Faithful Large Language Model Inference (2022) — 217 citations
  34. R3: Reinforced Ranker-Reader for Open-Domain Question Answering (2018) — 200 citations
  35. End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering (2021) — 192 citations
  36. Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue (2020) — 181 citations
  37. Reveal: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory (2022) — 178 citations
  38. Entities as Experts: Sparse Memory Access with Entity Supervision (2020) — 177 citations
  39. Internet-augmented language models through few-shot prompting for open-domain question answering (2022) — 177 citations
  40. Harvesting Paragraph-level Question-Answer Pairs from Wikipedia (2018) — 174 citations
  41. Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering (2019) — 173 citations
  42. Retrieval-Augmented Multimodal Language Modeling (2023) — 166 citations
  43. Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation (2024) — 165 citations
  44. Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension (2019) — 152 citations
  45. Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion (2022) — 150 citations
  46. Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions (2016) — 148 citations
  47. Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks (2017) — 144 citations
  48. Retrieval-based Language Models and Applications (2023) — 142 citations
  49. Retrieval Augmented Visual Question Answering with Outside Knowledge (2022) — 137 citations
  50. Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading (2019) — 111 citations

Most active researchers

By papers in this topic: a volume measure, not trust.