mlsanityData to 7 Oct 2026

Improving Passage Retrieval with Zero-Shot Question Generation

arXiv 2204.07496 ↗First posted 15 Apr 2022cs.CL cs.IRcited by 164

Not on the map. Why?

Cited by 32 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retrieved passages with a zero-shot question generation model, which uses a pre-trained language model to compute the probability of the input question conditioned on a retrieved passage. This approach can be applied on top of any retrieval method (e.g. neural or keyword-based), does not require any domain- or task-specific training (and therefore is expected to generalize better to data distribution shifts), and provides rich cross-attention between query and passage (i.e. it must explain every token in the question). When evaluated on a number of open-domain retrieval datasets, our re-ranker improves strong unsupervised retrieval models by 6%-18% absolute and strong supervised models by up to 12% in terms of top-20 passage retrieval accuracy. We also obtain new state-of-the-art results on full open-domain question answering by simply adding the new re-ranker to existing models with no further changes.

Key facts. Cited by 164 papers in the map (data through 7 Oct 2026). Builds on 35 of its 50 references that are in the map. First posted on arXiv 15 Apr 2022.

Builds on

35 of 50 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  8. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  9. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  10. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  11. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  12. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
23 more
  1. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  2. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  3. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  4. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  5. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  6. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  8. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  9. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  10. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  11. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  12. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 557
  13. 2021MetaICL: Learning to Learn In Contextcited by 450
  14. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  15. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  16. 2021Simple Entity-Centric Questions Challenge Dense Retrieverscited by 140
  17. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  18. 2021End-to-End Training of Neural Retrievers for Open-Domain Question Answeringcited by 75
  19. 2021Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?cited by 59
  20. 2021Mention Memory: incorporating textual knowledge into Transformers through entity mention attentioncited by 42
  21. 2021A Replication Study of Dense Passage Retrievercited by 37
  22. 2020Beyond [CLS] through Ranking by Generationcited by 20
  23. 2021Text-to-Text Multi-view Learning for Passage Re-rankingcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 12; 2023: 33; 2024: 49; 2025: 41; 2026: 29.

164 papers.

Sort:

By area:

  1. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  2. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  3. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
  4. 2023Adapting Language Models to Compress Contextscited by 350
  5. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  6. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 302
  7. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  8. 2022Promptagator: Few-shot Dense Retrieval From 8 Examplescited by 233
  9. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 114
  10. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 112
  11. 2023A Critical Evaluation of Evaluations for Long-form Question Answeringcited by 111
  12. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
38 more
  1. 2022Task-aware Retrieval with Instructionscited by 107
  2. 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 91
  3. 2022Coder Reviewer Reranking for Code Generationcited by 83
  4. 2023Zero-Shot Listwise Document Reranking with a Large Language Modelcited by 81
  5. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 81
  6. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learningcited by 58
  7. 2024Scaling Retrieval-Based Language Models with a Trillion-Token Datastorecited by 54
  8. 2023A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Modelscited by 53
  9. 2022Questions Are All You Need to Train a Dense Passage Retrievercited by 47
  10. 2024TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategycited by 47
  11. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  12. 2024Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankerscited by 42
  13. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  14. 2023Large Language Model Augmented Narrative Driven Recommendationscited by 31
  15. 2025Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-rankingcited by 30
  16. 2024Semantic Operators: A Declarative Model for Rich, AI-based Data Processingcited by 29
  17. 2023Rethinking the Role of Token Retrieval in Multi-Vector Retrievalcited by 28
  18. 2024APEER: Automatic Prompt Engineering Enhances Large Language Model Rerankingcited by 28
  19. 2024AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation Pipelinecited by 26
  20. 2023Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrievalcited by 24
  21. 2025REARANK: Reasoning Re-ranking Agent via Reinforcement Learningcited by 24
  22. 2024Ranking Manipulation for Conversational Search Enginescited by 23
  23. 2023Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-rankercited by 20
  24. 2023Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrievalcited by 20
  25. 2024Ranked List Truncation for Large Language Model-based Re-Rankingcited by 20
  26. 2024Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Modelscited by 20
  27. 2022Few-shot Reranking for Multi-hop QA via Language Model Promptingcited by 19
  28. 2023Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankerscited by 19
  29. 2024Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmarkcited by 19
  30. 2023AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrievalcited by 18
  31. 2024Query Performance Prediction using Relevance Judgments Generated by Large Language Modelscited by 18
  32. 2024Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankerscited by 17
  33. 2024DemoRank: Selecting Effective Demonstrations for Large Language Models in Ranking Taskcited by 17
  34. 2024EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generationcited by 17
  35. 2024LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Rankingcited by 16
  36. 2023Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answeringcited by 15
  37. 2024BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectivescited by 15
  38. 2025Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluationcited by 15

50 most cited of 164 All 164 (JSON)