Papers › Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single...

Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer

5 Dec 2022arXiv:2212.02027archive 2025-07-28

Zhengbao Jiang, Luyu Gao, Jun Araki, Haibo Ding, Zhiruo Wang, Jamie Callan, Graham Neubig

Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents to generate answers. Retrievers and readers are usually modeled separately, which necessitates a cumbersome implementation and is hard to train and adapt in an end-to-end fashion. In this paper, we revisit this design and eschew the separate architecture and training in favor of a single Transformer that performs Retrieval as Attention (ReAtt), and end-to-end training solely based on supervision from the end QA task. We demonstrate for the first time that a single model trained end-to-end can achieve both competitive retrieval and QA performance, matching or slightly outperforming state-of-the-art separately trained retrievers and readers. Moreover, end-to-end adaptation significantly boosts its performance on out-of-domain datasets in both supervised and unsupervised settings, making our model a simple and adaptable solution for knowledge-intensive tasks. Code and models are available at https://github.com/jzbjyb/ReAtt.

PaperPDFCode

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

Code

jzbjyb/reatt officialmentioned in papermentioned on GitHubpytorch 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.

Code Syntology ran Syntology

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

Tasks

Open-Domain Question AnsweringPassage RetrievalQuestion AnsweringRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Passage Retrieval Natural Questions ReAtt Precision@100 90.40 #1 of 10 Archive leaderboard report
Passage Retrieval Natural Questions ReAtt Precision@20 86.00 #1 of 10 Archive leaderboard report
Question Answering Natural Questions ReAtt EM 54.7 #6 of 47 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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