# Embedding-based Zero-shot Retrieval through Query Generation

arXiv: https://arxiv.org/abs/2009.10270 · HTML: https://mlsanity.com/paper/2009.10270/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2020.

## Built on by (most cited first, 24 of 24)

- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations](https://mlsanity.com/paper/2110.07581/) (2021)
- [Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2407.06992/) (2024)
- [Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey](https://mlsanity.com/paper/2208.03197/) (2022)
- [Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation](https://mlsanity.com/paper/2203.07735/) (2022)
- [Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks](https://mlsanity.com/paper/2301.12847/) (2023)
- [On the Robustness of Generative Retrieval Models: An Out-of-Distribution Perspective](https://mlsanity.com/paper/2306.12756/) (2023)
- [Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation](https://mlsanity.com/paper/2502.11181/) (2025)
- [Contrastive Document Representation Learning with Graph Attention Networks](https://mlsanity.com/paper/2110.10778/) (2021)
- [Improving Content Retrievability in Search with Controllable Query Generation](https://mlsanity.com/paper/2303.11648/) (2023)
- [Policy-Gradient Training of Language Models for Ranking](https://mlsanity.com/paper/2310.04407/) (2023)
- [Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models](https://mlsanity.com/paper/2506.00037/) (2025)
- [AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation](https://mlsanity.com/paper/2212.08841/) (2022)
- [SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval](https://mlsanity.com/paper/2307.10488/) (2023)
- [A Unified Language Model for Large Scale Search, Recommendation, and Reasoning](https://mlsanity.com/paper/2603.17533/) (2026)
- [JCSE: Contrastive Learning of Japanese Sentence Embeddings and Its Applications](https://mlsanity.com/paper/2301.08193/) (2023)
- [Improving Vietnamese Legal Document Retrieval using Synthetic Data](https://mlsanity.com/paper/2412.00657/) (2024)
- [Domain Adaptation for Japanese Sentence Embeddings with Contrastive Learning based on Synthetic Sentence Generation](https://mlsanity.com/paper/2503.09094/) (2025)
- [Domain Adaptation of Multilingual Semantic Search -- Literature Review](https://mlsanity.com/paper/2402.02932/) (2024)
- [IR2: Information Regularization for Information Retrieval](https://mlsanity.com/paper/2402.16200/) (2024)
- [Improving Document Retrieval Coherence for Semantically Equivalent Queries](https://mlsanity.com/paper/2508.07975/) (2025)
- [Semi-Supervised Synthetic Data Generation with Fine-Grained Relevance Control for Short Video Search Relevance Modeling](https://mlsanity.com/paper/2509.16717/) (2025)
- [Improving Scientific Document Retrieval with Academic Concept Index](https://mlsanity.com/paper/2601.00567/) (2026)

## 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