Papers › Large Dual Encoders Are Generalizable Retrievers

Large Dual Encoders Are Generalizable Retrievers

15 Dec 2021arXiv:2112.07899archive 2025-07-28

Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hernández Ábrego, Ji Ma, Vincent Y. Zhao, Yi Luan, Keith B. Hall, Ming-Wei Chang, Yinfei Yang

It has been shown that dual encoders trained on one domain often fail to generalize to other domains for retrieval tasks. One widespread belief is that the bottleneck layer of a dual encoder, where the final score is simply a dot-product between a query vector and a passage vector, is too limited to make dual encoders an effective retrieval model for out-of-domain generalization. In this paper, we challenge this belief by scaling up the size of the dual encoder model while keeping the bottleneck embedding size fixed. With multi-stage training, surprisingly, scaling up the model size brings significant improvement on a variety of retrieval tasks, especially for out-of-domain generalization. Experimental results show that our dual encoders, Generalizable T5-based dense Retrievers (GTR), outperform %ColBERT and existing sparse and dense retrievers on the BEIR dataset significantly. Most surprisingly, our ablation study finds that GTR is very data efficient, as it only needs 10% of MS Marco supervised data to achieve the best out-of-domain performance. All the GTR models are released at https://tfhub.dev/google/collections/gtr/1.

PaperPDFCode

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

google-research/t5x_retrieval mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Exploring Dual Encoder Architectures for Question Answering (arXiv:2204.07120; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
openmatch/coco-dr mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive... (arXiv:2210.15212; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result); 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

Domain GeneralizationPassage RetrievalRetrievalSentence RetrievalZero-shot Text Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Passage Retrieval PeerQA GTR-XL MRR 0.4142 #7 of 8 Archive leaderboard report
Passage Retrieval PeerQA GTR-XL Recall@10 0.6122 #7 of 8 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