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

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

8 Sep 2021Findings (EMNLP) 2021 11arXiv:2109.03502archive 2025-07-28

Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

KNOT-FIT-BUT/R2-D2 officialmentioned in paperpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Pruning the Index Contents for Memory Efficient Open-Domain QA (arXiv:2102.10697; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Open-Domain Question AnsweringPassage RetrievalQuestion AnsweringTriviaQA

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-Domain Question Answering Natural Questions R2-D2 \w HN-DPR Exact Match 55.9 #2 of 5 Archive leaderboard report
Passage Retrieval Natural Questions DPR+ELECTRA-large-extreader-reranker Precision@100 88.25 #5 of 10 Archive leaderboard report
Passage Retrieval Natural Questions DPR+ELECTRA-large-extreader-reranker Precision@20 85.26 #5 of 10 Archive leaderboard report
Passage Retrieval Natural Questions DPR+RoBERTa-base-crossencoder-reranker Precision@100 88.03 #6 of 10 Archive leaderboard report
Passage Retrieval Natural Questions DPR+RoBERTa-base-crossencoder-reranker Precision@20 84.46 #6 of 10 Archive leaderboard report
Question Answering Natural Questions R2-D2 (full) EM 55.9 #5 of 47 Archive leaderboard report
Question Answering Natural Questions (long) R2-D2 \w HN-DPR EM 55.9 #10 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections