mlsanityData to 14 Oct 2026

Efficient Passage Retrieval with Hashing for Open-domain Question Answering

arXiv 2106.00882 ↗First posted 2 Jun 2021cs.CL cs.IRcited by 53

Not on the map. Why?

Abstract (arXiv)

Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source. However, such retrieval models often require large memory to run because of the massive size of their passage index. In this paper, we introduce Binary Passage Retriever (BPR), a memory-efficient neural retrieval model that integrates a learning-to-hash technique into the state-of-the-art Dense Passage Retriever (DPR) to represent the passage index using compact binary codes rather than continuous vectors. BPR is trained with a multi-task objective over two tasks: efficient candidate generation based on binary codes and accurate reranking based on continuous vectors. Compared with DPR, BPR substantially reduces the memory cost from 65GB to 2GB without a loss of accuracy on two standard open-domain question answering benchmarks: Natural Questions and TriviaQA. Our code and trained models are available at https://github.com/studio-ousia/bpr.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

18 of 25 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  5. 2017Billion-scale similarity search with GPUscited by 2,497
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  8. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  9. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  10. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  11. 2017HashNet: Deep Learning to Hash by Continuationcited by 122
  12. 2016A Survey on Learning to Hashcited by 119
6 more
  1. 2015Feature Learning based Deep Supervised Hashing with Pairwise Labelscited by 59
  2. 2015Simultaneous Feature Learning and Hash Coding with Deep Neural Networkscited by 44
  3. 2015Learning to Hash for Indexing Big Data - A Surveycited by 39
  4. 2020A Memory Efficient Baseline for Open Domain Question Answeringcited by 32
  5. 2014On Symmetric and Asymmetric LSHs for Inner Product Searchcited by 23
  6. 2019Hashing based Answer Selectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 16; 2023: 5; 2024: 6; 2025: 4; 2026: 9.

53 papers.

Sort:

By area:

  1. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 476
  2. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 113
  3. 2022Task-aware Retrieval with Instructionscited by 107
  4. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  5. 2021A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniquescited by 69
  6. 2021The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpuscited by 60
  7. 2021Attacking Open-domain Question Answering by Injecting Misinformationcited by 41
  8. 2022Nonparametric Masked Language Modelingcited by 40
  9. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  10. 2021EntQA: Entity Linking as Question Answeringcited by 34
  11. 2022Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrievalcited by 27
  12. 2021A Proposed Conceptual Framework for a Representational Approach to Information Retrievalcited by 24
38 more
  1. 2024Balanced Data Sampling for Language Model Training with Clusteringcited by 23
  2. 2022Plug-and-Play Adaptation for Continuously-updated QAcited by 21
  3. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  4. 2021A Study on Token Pruning for ColBERTcited by 15
  5. 2025Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generationcited by 13
  6. 2021Exploring Dense Retrieval for Dialogue Response Selectioncited by 11
  7. 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11
  8. 2021Boosted Dense Retrievercited by 10
  9. 2022Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?cited by 10
  10. 2024Entity Retrieval for Answering Entity-Centric Questionscited by 10
  11. 2021Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answeringcited by 8
  12. 2022Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrievalcited by 7
  13. 2022Pre-trained Token-replaced Detection Model as Few-shot Learnercited by 7
  14. 2022A Study on the Efficiency and Generalization of Light Hybrid Retrieverscited by 7
  15. 2021Sparsifying Sparse Representations for Passage Retrieval by Top-k Maskingcited by 5
  16. 2022Query Expansion Using Contextual Clue Sampling with Language Modelscited by 5
  17. 2023Improving Dual-Encoder Training through Dynamic Indexes for Negative Miningcited by 5
  18. 2023Noise-Robust Dense Retrieval via Contrastive Alignment Post Trainingcited by 5
  19. 2023BTR: Binary Token Representations for Efficient Retrieval Augmented Language Modelscited by 5
  20. 2021Automatic Claim Review for Climate Science via Explanation Generationcited by 4
  21. 2022Two-Step Question Retrieval for Open-Domain QAcited by 4
  22. 2022Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrievalcited by 4
  23. 2024Crafting the Path: Robust Query Rewriting for Information Retrievalcited by 4
  24. 2025REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processingcited by 4
  25. 2026What Limits Does Quantization Place on Dense Top-k Retrieval? A Theoretical Studycited by 4
  26. 2022Knowledge Base Index Compression via Dimensionality and Precision Reductioncited by 2
  27. 2023MFBE: Leveraging Multi-Field Information of FAQs for Efficient Dense Retrievalcited by 1
  28. 2026Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarkscited by 1
  29. 2026From Volume to Value: Preference-Aligned Memory Construction for On-Device RAGcited by 1
  30. 2026Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiabilitycited by 1
  31. 2026Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scalecited by 1
  32. 2026Matryoshka Hash Representations for Model-Aware Compact Semantic Retrievalcited by 1
  33. 2021Quality and Cost Trade-offs in Passage Re-ranking Taskcited by 0
  34. 2022An Open-Domain QA System for e-Governancecited by 0
  35. 2022Enhanced vectors for top-k document retrieval in Question Answeringcited by 0
  36. 2023KoBigBird-large: Transformation of Transformer for Korean Language Understandingcited by 0
  37. 2024Semi-Parametric Retrieval via Binary Bag-of-Tokens Indexcited by 0
  38. 2025Do LLMs and Humans Find the Same Questions Difficult? A Case Study on Japanese Quiz Answeringcited by 0

50 most cited of 53 All 53 (JSON)