mlsanityData to 7 Oct 2026

Latent Retrieval for Weakly Supervised Open Domain Question Answering

arXiv 1906.00300 ↗First posted 1 Jun 2019cs.CLcited by 691

Not on the map. Why?

Cited by 102 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. We argue that both are suboptimal, since gold evidence is not always available, and QA is fundamentally different from IR. We show for the first time that it is possible to jointly learn the retriever and reader from question-answer string pairs and without any IR system. In this setting, evidence retrieval from all of Wikipedia is treated as a latent variable. Since this is impractical to learn from scratch, we pre-train the retriever with an Inverse Cloze Task. We evaluate on open versions of five QA datasets. On datasets where the questioner already knows the answer, a traditional IR system such as BM25 is sufficient. On datasets where a user is genuinely seeking an answer, we show that learned retrieval is crucial, outperforming BM25 by up to 19 points in exact match.

Key facts. Cited by 691 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 138; 2022: 143; 2023: 111; 2024: 156; 2025: 90; 2026: 51.

691 papers.

Sort:

By area:

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  5. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  6. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  7. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  8. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  9. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  10. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  11. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  12. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
38 more
  1. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  2. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  3. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 452
  4. 2022Memory-Based Model Editing at Scalecited by 443
  5. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  6. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 402
  7. 2023Augmented Language Models: a Surveycited by 398
  8. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 358
  9. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  10. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 296
  11. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  12. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  13. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  14. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 231
  15. 2021Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrievalcited by 203
  16. 2023Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?cited by 203
  17. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 198
  18. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 197
  19. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  20. 2024An Empirical Study of Mamba-based Language Modelscited by 177
  21. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
  22. 2023AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotatorscited by 171
  23. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  24. 2021Hurdles to Progress in Long-form Question Answeringcited by 166
  25. 2023UniIR: Training and Benchmarking Universal Multimodal Information Retrieverscited by 165
  26. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 165
  27. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
  28. 2021Condenser: a Pre-training Architecture for Dense Retrievalcited by 162
  29. 2022A Survey on Retrieval-Augmented Text Generationcited by 157
  30. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 153
  31. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  32. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  33. 2021SituatedQA: Incorporating Extra-Linguistic Contexts into QAcited by 145
  34. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 144
  35. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142
  36. 2021Simple Entity-Centric Questions Challenge Dense Retrieverscited by 140
  37. 2021Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Predictioncited by 137
  38. 2022KNN-Diffusion: Image Generation via Large-Scale Retrievalcited by 135

50 most cited of 691 All 691 (JSON)