mlsanityData to 7 Oct 2026

Embedding-based Zero-shot Retrieval through Query Generation

arXiv 2009.10270 ↗First posted 22 Sep 2020cs.IRcited by 24

Not on the map. Why?

Abstract (arXiv)

Passage retrieval addresses the problem of locating relevant passages, usually from a large corpus, given a query. In practice, lexical term-matching algorithms like BM25 are popular choices for retrieval owing to their efficiency. However, term-based matching algorithms often miss relevant passages that have no lexical overlap with the query and cannot be finetuned to downstream datasets. In this work, we consider the embedding-based two-tower architecture as our neural retrieval model. Since labeled data can be scarce and because neural retrieval models require vast amounts of data to train, we propose a novel method for generating synthetic training data for retrieval. Our system produces remarkable results, significantly outperforming BM25 on 5 out of 6 datasets tested, by an average of 2.45 points for Recall@1. In some cases, our model trained on synthetic data can even outperform the same model trained on real data

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 6; 2024: 4; 2025: 5; 2026: 2.

24 papers.

Sort:

By area:

  1. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  2. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  3. 2021Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representationscited by 27
  4. 2024Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspectivecited by 15
  5. 2022Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Surveycited by 14
  6. 2022Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbationcited by 10
  7. 2023Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networkscited by 9
  8. 2023On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspectivecited by 8
  9. 2021Contrastive Document Representation Learning with Graph Attention Networkscited by 6
  10. 2023Improving Content Retrievability in Search with Controllable Query Generationcited by 6
  11. 2025Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generationcited by 6
  12. 2023Policy-Gradient Training of Language Models for Rankingcited by 5
12 more
  1. 2025Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Modelscited by 5
  2. 2022AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentationcited by 3
  3. 2023SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrievalcited by 2
  4. 2026A Unified Language Model for Large Scale Search, Recommendation, and Reasoningcited by 2
  5. 2023JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its Applicationscited by 1
  6. 2024Improving Vietnamese Legal Document Retrieval using Synthetic Datacited by 1
  7. 2025Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generationcited by 1
  8. 2024Domain Adaptation of Multilingual Semantic Search -- Literature Reviewcited by 0
  9. 2024IR2: Information Regularization for Information Retrievalcited by 0
  10. 2025Improving Document Retrieval Coherence for Semantically Equivalent Queriescited by 0
  11. 2025Semi-Supervised Synthetic Data Generation with Fine-Grained Relevance Control for Short Video Search Relevance Modelingcited by 0
  12. 2026Improving Scientific Document Retrieval with Academic Concept Indexcited by 0