mlsanityData to 7 Oct 2026

End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering

arXiv 2106.05346 ↗First posted 9 Jun 2021cs.CL cs.AI cs.IRcited by 133

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. We model retrieval decisions as latent variables over sets of relevant documents. Since marginalizing over sets of retrieved documents is computationally hard, we approximate this using an expectation-maximization algorithm. We iteratively estimate the value of our latent variable (the set of relevant documents for a given question) and then use this estimate to update the retriever and reader parameters. We hypothesize that such end-to-end training allows training signals to flow to the reader and then to the retriever better than staged-wise training. This results in a retriever that is able to select more relevant documents for a question and a reader that is trained on more accurate documents to generate an answer. Experiments on three benchmark datasets demonstrate that our proposed method outperforms all existing approaches of comparable size by 2-3% absolute exact match points, achieving new state-of-the-art results. Our results also demonstrate the feasibility of learning to retrieve to improve answer generation without explicit supervision of retrieval decisions.

Key facts. Cited by 133 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 31 of its 58 references that are in the map. First posted on arXiv 9 Jun 2021.

Builds on

31 of 58 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  7. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  8. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  9. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  10. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  11. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  12. 2019Language Models as Knowledge Bases?cited by 1,922
19 more
  1. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,829
  2. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  3. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  4. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  5. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  6. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 719
  7. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  8. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  9. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  10. 2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 213
  11. 2020Nearest Neighbor Machine Translationcited by 209
  12. 2019Episodic Memory in Lifelong Language Learningcited by 188
  13. 2017Simple and Effective Multi-Paragraph Reading Comprehensioncited by 120
  14. 2019Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answeringcited by 96
  15. 2021Adaptive Semiparametric Language Modelscited by 83
  16. 2019A Discrete Hard EM Approach for Weakly Supervised Question Answeringcited by 78
  17. 2021End-to-End Training of Neural Retrievers for Open-Domain Question Answeringcited by 75
  18. 2020Augmenting Transformers with KNN-Based Composite Memory for Dialoguecited by 53
  19. 2020RECONSIDER: Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answeringcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 35; 2023: 27; 2024: 40; 2025: 18; 2026: 7.

133 papers.

Sort:

By area:

  1. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  2. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  4. 2023Active Retrieval Augmented Generationcited by 506
  5. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  6. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  7. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  8. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  9. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  10. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  11. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 180
  12. 2023SlideVQA: A Dataset for Document Visual Question Answering on Multiple Imagescited by 175
38 more
  1. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  2. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
  3. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  4. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142
  5. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 134
  6. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  7. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answeringcited by 126
  8. 2022StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Modelscited by 123
  9. 2022REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memorycited by 122
  10. 2022Training Language Models with Memory Augmentationcited by 112
  11. 2023Evaluating Open-Domain Question Answering in the Era of Large Language Modelscited by 110
  12. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
  13. 2023Improving Language Models via Plug-and-Play Retrieval Feedbackcited by 87
  14. 2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
  15. 2021Adversarial Retriever-Ranker for dense text retrievalcited by 82
  16. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  17. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 70
  18. 2022FiD-Light: Efficient and Effective Retrieval-Augmented Text Generationcited by 63
  19. 2024When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentationcited by 59
  20. 2024Instruction-tuned Language Models are Better Knowledge Learnerscited by 54
  21. 2022Questions Are All You Need to Train a Dense Passage Retrievercited by 47
  22. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Modelscited by 47
  23. 2021Learning to Retrieve Passages without Supervisioncited by 46
  24. 2022Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformercited by 45
  25. 2022QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphscited by 42
  26. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  27. 2022Standing on the Shoulders of Giant Frozen Language Modelscited by 33
  28. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewardscited by 33
  29. 2025R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learningcited by 32
  30. 2023Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Trainingcited by 31
  31. 2022A Survey of Knowledge-Intensive NLP with Pre-Trained Language Modelscited by 30
  32. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directionscited by 30
  33. 2024JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claimscited by 29
  34. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrievalcited by 28
  35. 2023ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrievalcited by 26
  36. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processingcited by 25
  37. 2022Decoupled Context Processing for Context Augmented Language Modelingcited by 24
  38. 2024Manipulating Large Language Models to Increase Product Visibilitycited by 24

50 most cited of 133 All 133 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding
  2. 2026Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
  3. 2024Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts
  4. 2024REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering
  5. 2024Answerability in Retrieval-Augmented Open-Domain Question Answering
  6. 2025Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering
  7. 2023Prompt Generate Train (PGT): Few-shot Domain Adaption of Retrieval Augmented Generation Models for Open Book Question-Answering
  8. 2024W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering