# Towards Robust Neural Retrieval Models with Synthetic Pre-Training

arXiv: https://arxiv.org/abs/2104.07800 · HTML: https://mlsanity.com/paper/2104.07800/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 15 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [Pre-training Tasks for Embedding-based Large-scale Retrieval](https://mlsanity.com/paper/2002.03932/) (2020)
- [Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets](https://mlsanity.com/paper/2008.02637/) (2020)
- [End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems](https://mlsanity.com/paper/2010.06028/) (2020)
- [Multi-Stage Pre-training for Low-Resource Domain Adaptation](https://mlsanity.com/paper/2010.05904/) (2020)

## Built on by (most cited first, 9 of 9)

- [Learning to Retrieve Passages without Supervision](https://mlsanity.com/paper/2112.07708/) (2021)
- [What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary](https://mlsanity.com/paper/2212.10380/) (2022)
- [Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering](https://mlsanity.com/paper/2203.06942/) (2022)
- [Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering](https://mlsanity.com/paper/2305.17080/) (2023)
- [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)
- [Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrieval](https://mlsanity.com/paper/2204.11373/) (2022)
- [Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval](https://mlsanity.com/paper/2302.01626/) (2023)
- [Domain Adaptation of Multilingual Semantic Search -- Literature Review](https://mlsanity.com/paper/2402.02932/) (2024)

## Abstract (arXiv)

Recent work has shown that commonly available machine reading comprehension (MRC) datasets can be used to train high-performance neural information retrieval (IR) systems. However, the evaluation of neural IR has so far been limited to standard supervised learning settings, where they have outperformed traditional term matching baselines. We conduct in-domain and out-of-domain evaluations of neural IR, and seek to improve its robustness across different scenarios, including zero-shot settings. We show that synthetic training examples generated using a sequence-to-sequence generator can be effective towards this goal: in our experiments, pre-training with synthetic examples improves retrieval performance in both in-domain and out-of-domain evaluation on five different test sets.