mlsanityData to 14 Oct 2026

Promptagator: Few-shot Dense Retrieval From 8 Examples

arXiv 2209.11755 ↗First posted 23 Sep 2022cs.CL cs.IRcited by 235

Not on the map. Why?

Cited by 35 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Much recent research on information retrieval has focused on how to transfer from one task (typically with abundant supervised data) to various other tasks where supervision is limited, with the implicit assumption that it is possible to generalize from one task to all the rest. However, this overlooks the fact that there are many diverse and unique retrieval tasks, each targeting different search intents, queries, and search domains. In this paper, we suggest to work on Few-shot Dense Retrieval, a setting where each task comes with a short description and a few examples. To amplify the power of a few examples, we propose Prompt-base Query Generation for Retriever (Promptagator), which leverages large language models (LLM) as a few-shot query generator, and creates task-specific retrievers based on the generated data. Powered by LLM's generalization ability, Promptagator makes it possible to create task-specific end-to-end retrievers solely based on a few examples {without} using Natural Questions or MS MARCO to train %question generators or dual encoders. Surprisingly, LLM prompting with no more than 8 examples allows dual encoders to outperform heavily engineered models trained on MS MARCO like ColBERT v2 by more than 1.2 nDCG on average on 11 retrieval sets. Further training standard-size re-rankers using the same generated data yields another 5.0 point nDCG improvement. Our studies determine that query generation can be far more effective than previously observed, especially when a small amount of task-specific knowledge is given.

Key facts. Cited by 235 papers in the map (data through 14 Oct 2026). Builds on 57 of its 76 references that are in the map. First posted on arXiv 23 Sep 2022.

Builds on

57 of 76 references.

References · 57

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  7. 2022Emergent Abilities of Large Language Modelscited by 2,512
  8. 2017Billion-scale similarity search with GPUscited by 2,497
  9. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  10. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  11. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  12. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
38 more
  1. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  2. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  3. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  4. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  6. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  7. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  8. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  9. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 669
  10. 2019Passage Re-ranking with BERTcited by 645
  11. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  12. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  13. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 413
  14. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  15. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
  16. 2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 214
  17. 2021Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrievalcited by 203
  18. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 200
  19. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 176
  20. 2019Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoringcited by 165
  21. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 165
  22. 2021Condenser: a Pre-training Architecture for Dense Retrievalcited by 162
  23. 2020Pre-training Tasks for Embedding-based Large-scale Retrievalcited by 153
  24. 2020Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillationcited by 145
  25. 2019Synthetic QA Corpora Generation with Roundtrip Consistencycited by 143
  26. 2021Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Modelscited by 139
  27. 2021SPLADE v2: Sparse Lexical and Expansion Model for Information Retrievalcited by 127
  28. 2017A Deep Relevance Matching Model for Ad-hoc Retrievalcited by 126
  29. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  30. 2021COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted Listcited by 113
  31. 2020Few-Shot Text Generation with Pattern-Exploiting Trainingcited by 87
  32. 2017End-to-End Neural Ad-hoc Ranking with Kernel Poolingcited by 85
  33. 2021Adversarial Retriever-Ranker for dense text retrievalcited by 83
  34. 2020End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systemscited by 65
  35. 2021Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?cited by 60
  36. 2015Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrievalcited by 54
  37. 2021Neural Data Augmentation via Example Extrapolationcited by 54
  38. 2021Domain-matched Pre-training Tasks for Dense Retrievalcited by 53

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 10; 2023: 66; 2024: 69; 2025: 51; 2026: 39.

235 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,576
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  3. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  4. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  5. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
  6. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  7. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 307
  8. 2023Improving Text Embeddings with Large Language Modelscited by 303
  9. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 284
  10. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 265
  11. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  12. 2024GME: Improving Universal Multimodal Retrieval by Multimodal LLMscited by 170
38 more
  1. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 143
  2. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 135
  3. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 118
  4. 2022Task-aware Retrieval with Instructionscited by 107
  5. 2023Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documentscited by 104
  6. 2025Gemini Embedding: Generalizable Embeddings from Geminicited by 94
  7. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
  8. 2023Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkerscited by 87
  9. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 83
  10. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  11. 2023Zero-Shot Listwise Document Reranking with a Large Language Modelcited by 82
  12. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
  13. 2025ReasonIR: Training Retrievers for Reasoning Taskscited by 77
  14. 2023InPars-v2: Large Language Models as Efficient Dataset Generators for Information Retrievalcited by 73
  15. 2023RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Modelscited by 70
  16. 2024Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Modelscited by 61
  17. 2024Arctic-Embed 2.0: Multilingual Retrieval Without Compromisecited by 58
  18. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52
  19. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Modelscited by 50
  20. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  21. 2024Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Modelscited by 40
  22. 2025TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generationcited by 40
  23. 2023Neural Retrievers are Biased Towards LLM-Generated Contentcited by 38
  24. 2024BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrieverscited by 38
  25. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  26. 2023UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankerscited by 37
  27. 2023Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Modelscited by 35
  28. 2023Rethinking the Role of Token Retrieval in Multi-Vector Retrievalcited by 31
  29. 2023Large Language Model Augmented Narrative Driven Recommendationscited by 31
  30. 2023Large Language Models are Built-in Autoregressive Search Enginescited by 27
  31. 2025RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defectscited by 27
  32. 2023Large Language Models are Strong Zero-Shot Retrievercited by 26
  33. 2023Asking Clarification Questions to Handle Ambiguity in Open-Domain QAcited by 26
  34. 2023When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasetscited by 26
  35. 2025Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generationcited by 26
  36. 2022QAmeleon: Multilingual QA with Only 5 Examplescited by 25
  37. 2023Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrievalcited by 24
  38. 2023The Life Cycle of Knowledge in Big Language Models: A Surveycited by 23

50 most cited of 235 All 235 (JSON)