mlsanityData to 7 Oct 2026

R2-D2: A Modular Baseline for Open-Domain Question Answering

arXiv 2109.03502 ↗First posted 8 Sep 2021cs.CL cs.IR cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

This work presents a novel four-stage open-domain QA pipeline R2-D2 (Rank twice, reaD twice). The pipeline is composed of a retriever, passage reranker, extractive reader, generative reader and a mechanism that aggregates the final prediction from all system's components. We demonstrate its strength across three open-domain QA datasets: NaturalQuestions, TriviaQA and EfficientQA, surpassing state-of-the-art on the first two. Our analysis demonstrates that: (i) combining extractive and generative reader yields absolute improvements up to 5 exact match and it is at least twice as effective as the posterior averaging ensemble of the same models with different parameters, (ii) the extractive reader with fewer parameters can match the performance of the generative reader on extractive QA datasets.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 39 of its 53 references that are in the map. First posted on arXiv 8 Sep 2021.

Builds on

39 of 53 references.

References · 39

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2020Longformer: The Long-Document Transformercited by 3,362
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  10. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  11. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  12. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
27 more
  1. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  2. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  3. 2019Passage Re-ranking with BERTcited by 629
  4. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  5. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  6. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  7. 2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 213
  8. 2019Multi-Stage Document Ranking with BERTcited by 200
  9. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  10. 2019End-to-End Open-Domain Question Answering with BERTserinicited by 152
  11. 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
  12. 2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
  13. 2017Simple and Effective Multi-Paragraph Reading Comprehensioncited by 120
  14. 2019Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answeringcited by 96
  15. 2019A Discrete Hard EM Approach for Weakly Supervised Question Answeringcited by 78
  16. 2020Relevance-guided Supervision for OpenQA with ColBERTcited by 71
  17. 2019Knowledge Guided Text Retrieval and Reading for Open Domain Question Answeringcited by 59
  18. 2019Understanding the Behaviors of BERT in Rankingcited by 49
  19. 2021UnitedQA: A Hybrid Approach for Open Domain Question Answeringcited by 42
  20. 2020A Memory Efficient Baseline for Open Domain Question Answeringcited by 32
  21. 2020Is Retriever Merely an Approximator of Reader?cited by 30
  22. 2021Rider: Reader-Guided Passage Reranking for Open-Domain Question Answeringcited by 28
  23. 2018Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answeringcited by 24
  24. 2020Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answeringcited by 17
  25. 2020Progressively Pretrained Dense Corpus Index for Open-Domain Question Answeringcited by 11
  26. 2020RECONSIDER: Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answeringcited by 9
  27. 2020Rethinking the Objectives of Extractive Question Answeringcited by 6

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 13; 2023: 14; 2024: 6.

37 papers.

Sort:

By area:

  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  2. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  3. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  4. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  5. 2023Evaluating Open-Domain Question Answering in the Era of Large Language Modelscited by 110
  6. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
  7. 2022FiD-Light: Efficient and Effective Retrieval-Augmented Text Generationcited by 63
  8. 2022Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformercited by 45
  9. 2021Evidentiality-guided Generation for Knowledge-Intensive NLP Taskscited by 40
  10. 2023Merging Generated and Retrieved Knowledge for Open-Domain QAcited by 36
  11. 2022Standing on the Shoulders of Giant Frozen Language Modelscited by 33
  12. 2021Open Domain Question Answering with A Unified Knowledge Interfacecited by 32
25 more
  1. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  2. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  3. 2021You Only Need One Model for Open-domain Question Answeringcited by 17
  4. 2024BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanismcited by 12
  5. 2022MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languagescited by 11
  6. 2023GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Rankingcited by 11
  7. 2022Multi-Task Retrieval-Augmented Text Generation with Relevance Samplingcited by 10
  8. 2024RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generationcited by 10
  9. 2023Expository Text Generation: Imitate, Retrieve, Paraphrasecited by 8
  10. 2022Optimizing Test-Time Query Representations for Dense Retrievalcited by 6
  11. 2022Knowledge Transfer from Answer Ranking to Answer Generationcited by 6
  12. 2022Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Modelscited by 6
  13. 2021Simple Questions Generate Named Entity Recognition Datasetscited by 5
  14. 2022FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answeringcited by 5
  15. 2023RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answeringcited by 4
  16. 2023Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questionscited by 3
  17. 2023Learning Answer Generation using Supervision from Automatic Question Answering Evaluatorscited by 3
  18. 2023When to Read Documents or QA History: On Unified and Selective Open-domain QAcited by 3
  19. 2023ReFIT: Relevance Feedback from a Reranker during Inferencecited by 2
  20. 2023Exploiting Abstract Meaning Representation for Open-Domain Question Answeringcited by 2
  21. 2024FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selectioncited by 2
  22. 2022IDIAPers @ Causal News Corpus 2022: Extracting Cause-Effect-Signal Triplets via Pre-trained Autoregressive Language Modelcited by 1
  23. 2023Dynamic Retrieval-Augmented Generationcited by 1
  24. 2024GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillationcited by 1
  25. 2024SUKHSANDESH: An Avatar Therapeutic Question Answering Platform for Sexual Education in Rural Indiacited by 0