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

arXiv: https://arxiv.org/abs/2109.03502 · HTML: https://mlsanity.com/paper/2109.03502/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 53 references that are in the map.
- First posted on arXiv 8 Sep 2021.

## Builds on (most cited first, 30 of 39)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Distilling Knowledge from Reader to Retriever for Question Answering](https://mlsanity.com/paper/2012.04584/) (2020)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [End-to-End Open-Domain Question Answering with BERTserini](https://mlsanity.com/paper/1902.01718/) (2019)
- [Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering](https://mlsanity.com/paper/1911.10470/) (2019)
- [Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets](https://mlsanity.com/paper/2008.02637/) (2020)
- [Simple and Effective Multi-Paragraph Reading Comprehension](https://mlsanity.com/paper/1710.10723/) (2017)
- [Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering](https://mlsanity.com/paper/1908.08167/) (2019)
- [A Discrete Hard EM Approach for Weakly Supervised Question Answering](https://mlsanity.com/paper/1909.04849/) (2019)
- [Relevance-guided Supervision for OpenQA with ColBERT](https://mlsanity.com/paper/2007.00814/) (2020)
- [Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering](https://mlsanity.com/paper/1911.03868/) (2019)
- [Understanding the Behaviors of BERT in Ranking](https://mlsanity.com/paper/1904.07531/) (2019)

## Built on by (most cited first, 30 of 37)

- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Internet-augmented language models through few-shot prompting for open-domain question answering](https://mlsanity.com/paper/2203.05115/) (2022)
- [Evaluating Open-Domain Question Answering in the Era of Large Language Models](https://mlsanity.com/paper/2305.06984/) (2023)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2209.14290/) (2022)
- [Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer](https://mlsanity.com/paper/2212.02027/) (2022)
- [Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2112.08688/) (2021)
- [Merging Generated and Retrieved Knowledge for Open-Domain QA](https://mlsanity.com/paper/2310.14393/) (2023)
- [Standing on the Shoulders of Giant Frozen Language Models](https://mlsanity.com/paper/2204.10019/) (2022)
- [Open Domain Question Answering with A Unified Knowledge Interface](https://mlsanity.com/paper/2110.08417/) (2021)
- [A Survey for Efficient Open Domain Question Answering](https://mlsanity.com/paper/2211.07886/) (2022)
- [Chain-of-Skills: A Configurable Model for Open-domain Question Answering](https://mlsanity.com/paper/2305.03130/) (2023)
- [You Only Need One Model for Open-domain Question Answering](https://mlsanity.com/paper/2112.07381/) (2021)
- [BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism](https://mlsanity.com/paper/2412.17933/) (2024)
- [MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages](https://mlsanity.com/paper/2207.00758/) (2022)
- [GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking](https://mlsanity.com/paper/2305.18144/) (2023)
- [Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling](https://mlsanity.com/paper/2207.03030/) (2022)
- [RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation](https://mlsanity.com/paper/2406.05794/) (2024)
- [Expository Text Generation: Imitate, Retrieve, Paraphrase](https://mlsanity.com/paper/2305.03276/) (2023)
- [Optimizing Test-Time Query Representations for Dense Retrieval](https://mlsanity.com/paper/2205.12680/) (2022)
- [Knowledge Transfer from Answer Ranking to Answer Generation](https://mlsanity.com/paper/2210.12865/) (2022)
- [Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models](https://mlsanity.com/paper/2211.00915/) (2022)
- [Simple Questions Generate Named Entity Recognition Datasets](https://mlsanity.com/paper/2112.08808/) (2021)
- [FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering](https://mlsanity.com/paper/2211.10147/) (2022)
- [RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering](https://mlsanity.com/paper/2305.17041/) (2023)
- [Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions](https://mlsanity.com/paper/2305.14441/) (2023)
- [Learning Answer Generation using Supervision from Automatic Question Answering Evaluators](https://mlsanity.com/paper/2305.15344/) (2023)
- [When to Read Documents or QA History: On Unified and Selective Open-domain QA](https://mlsanity.com/paper/2306.04176/) (2023)

## 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.