mlsanityData to 7 Oct 2026

A Memory Efficient Baseline for Open Domain Question Answering

arXiv 2012.15156 ↗First posted 30 Dec 2020cs.CLcited by 32

Not on the map. Why?

Abstract (arXiv)

Recently, retrieval systems based on dense representations have led to important improvements in open-domain question answering, and related tasks. While very effective, this approach is also memory intensive, as the dense vectors for the whole knowledge source need to be kept in memory. In this paper, we study how the memory footprint of dense retriever-reader systems can be reduced. We consider three strategies to reduce the index size: dimension reduction, vector quantization and passage filtering. We evaluate our approach on two question answering benchmarks: TriviaQA and NaturalQuestions, showing that it is possible to get competitive systems using less than 6Gb of memory.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 8; 2023: 3; 2024: 5; 2025: 0; 2026: 1.

32 papers.

Sort:

By area:

  1. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  2. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  4. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  5. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 198
  6. 2021Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrievalcited by 63
  7. 2021Efficient Passage Retrieval with Hashing for Open-domain Question Answeringcited by 53
  8. 2021NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learnedcited by 52
  9. 2021Multilingual Autoregressive Entity Linkingcited by 50
  10. 2022Nonparametric Masked Language Modelingcited by 39
  11. 2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
  12. 2021A Proposed Conceptual Framework for a Representational Approach to Information Retrievalcited by 24
20 more
  1. 2021Highly Parallel Autoregressive Entity Linking with Discriminative Correctioncited by 21
  2. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  3. 2024MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answeringcited by 17
  4. 2021Boosted Dense Retrievercited by 10
  5. 2022Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?cited by 10
  6. 2021Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answeringcited by 8
  7. 2023ESPN: Memory-Efficient Multi-Vector Information Retrievalcited by 7
  8. 2021Pruning the Index Contents for Memory Efficient Open-Domain QAcited by 6
  9. 2024Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generationcited by 6
  10. 2021Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answeringcited by 5
  11. 2023LeanVec: Searching vectors faster by making them fitcited by 5
  12. 2022Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrievalcited by 4
  13. 2022Knowledge Base Index Compression via Dimensionality and Precision Reductioncited by 2
  14. 2023Strong and Efficient Baselines for Open Domain Conversational Question Answeringcited by 2
  15. 2024MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sourcescited by 2
  16. 2022Bridging the Training-Inference Gap for Dense Phrase Retrievalcited by 1
  17. 2022Enhanced vectors for top-k document retrieval in Question Answeringcited by 0
  18. 2024Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorizationcited by 0
  19. 2024GleanVec: Accelerating vector search with minimalist nonlinear dimensionality reductioncited by 0
  20. 2026Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priorscited by 0