mlsanityData to 7 Oct 2026

Precise Zero-Shot Dense Retrieval without Relevance Labels

arXiv 2212.10496 ↗First posted 20 Dec 2022cs.IR cs.CLcited by 508

Not on the map. Why?

Cited by 217 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the difficulty of zero-shot learning and encoding relevance. Instead, we propose to pivot through Hypothetical Document Embeddings~(HyDE). Given a query, HyDE first zero-shot instructs an instruction-following language model (e.g. InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is unreal and may contain false details. Then, an unsupervised contrastively learned encoder~(e.g. Contriever) encodes the document into an embedding vector. This vector identifies a neighborhood in the corpus embedding space, where similar real documents are retrieved based on vector similarity. This second step ground the generated document to the actual corpus, with the encoder's dense bottleneck filtering out the incorrect details. Our experiments show that HyDE significantly outperforms the state-of-the-art unsupervised dense retriever Contriever and shows strong performance comparable to fine-tuned retrievers, across various tasks (e.g. web search, QA, fact verification) and languages~(e.g. sw, ko, ja).

Key facts. Cited by 508 papers in the map (data through 7 Oct 2026). Builds on 41 of its 64 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

41 of 64 references.

References · 41

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  9. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  10. 2017Billion-scale similarity search with GPUscited by 2,477
  11. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  12. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
29 more
  1. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  2. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  3. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  5. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  6. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  7. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  8. 2020Fact or Fiction: Verifying Scientific Claimscited by 546
  9. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 486
  10. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  11. 2021MetaICL: Learning to Learn In Contextcited by 450
  12. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  13. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  14. 2020Overview of the TREC 2019 deep learning trackcited by 282
  15. 2022Transformer Memory as a Differentiable Search Indexcited by 242
  16. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  17. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  18. 2021Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrievalcited by 203
  19. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 198
  20. 2020CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claimscited by 195
  21. 2021Overview of the TREC 2020 deep learning trackcited by 193
  22. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
  23. 2021Condenser: a Pre-training Architecture for Dense Retrievalcited by 162
  24. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  25. 2021Mr. TyDi: A Multi-lingual Benchmark for Dense Retrievalcited by 118
  26. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 112
  27. 2022Task-aware Retrieval with Instructionscited by 107
  28. 2022COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learningcited by 19
  29. 2022Generative Multi-hop Retrievalcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 45; 2024: 113; 2025: 149; 2026: 201.

508 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2023Active Retrieval Augmented Generationcited by 506
  3. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  4. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
  5. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  6. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  7. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  8. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
  9. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 302
  10. 2023Query2doc: Query Expansion with Large Language Modelscited by 146
  11. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentationcited by 118
  12. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
38 more
  1. 2023Zero-Shot Listwise Document Reranking with a Large Language Modelcited by 81
  2. 2024A Survey on Retrieval-Augmented Text Generation for Large Language Modelscited by 77
  3. 2023RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Modelscited by 69
  4. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 69
  5. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  6. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Pathscited by 60
  7. 2024KG-RAG: Bridging the Gap Between Knowledge and Creativitycited by 55
  8. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52
  9. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  10. 2024CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Modelscited by 50
  11. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 50
  12. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agentscited by 49
  13. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documentscited by 48
  14. 2024RS-Agent: Automating Remote Sensing Tasks through Intelligent Agentcited by 46
  15. 2025Retrieval-Augmented Generation with Hierarchical Knowledgecited by 46
  16. 2025A Survey of Large Language Model Agents for Question Answeringcited by 46
  17. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  18. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 41
  19. 2023Prompt2Model: Generating Deployable Models from Natural Language Instructionscited by 40
  20. 2024On the Structural Memory of LLM Agentscited by 37
  21. 2024LumberChunker: Long-Form Narrative Document Segmentationcited by 36
  22. 2024Knowledge Boundary of Large Language Models: A Surveycited by 36
  23. 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
  24. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  25. 2025Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learningcited by 32
  26. 2023Large Language Model Augmented Narrative Driven Recommendationscited by 31
  27. 2023PDFTriage: Question Answering over Long, Structured Documentscited by 29
  28. 2024CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Searchcited by 29
  29. 2024Mask-based Membership Inference Attacks for Retrieval-Augmented Generationcited by 29
  30. 2025KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAGcited by 29
  31. 2024Scaling Laws For Dense Retrievalcited by 28
  32. 2024APEER: Automatic Prompt Engineering Enhances Large Language Model Rerankingcited by 28
  33. 2024Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QAcited by 28
  34. 2024AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipelinecited by 26
  35. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAGcited by 26
  36. 2025SciSciGPT: Advancing Human-AI Collaboration in the Science of Sciencecited by 26
  37. 2023Large Language Models are Strong Zero-Shot Retrievercited by 25
  38. 2023When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasetscited by 25

50 most cited of 508 All 508 (JSON)