# End-to-End Training of Neural Retrievers for Open-Domain Question Answering

arXiv: https://arxiv.org/abs/2101.00408 · HTML: https://mlsanity.com/paper/2101.00408/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 2 Jan 2021.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [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)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [Pre-training Tasks for Embedding-based Large-scale Retrieval](https://mlsanity.com/paper/2002.03932/) (2020)
- [Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)](https://mlsanity.com/paper/1405.5869/) (2014)
- [Practical and Optimal LSH for Angular Distance](https://mlsanity.com/paper/1509.02897/) (2015)
- [Pre-training via Paraphrasing](https://mlsanity.com/paper/2006.15020/) (2020)
- [Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge](https://mlsanity.com/paper/2007.00849/) (2020)

## Built on by (most cited first, 30 of 75)

- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Large Dual Encoders Are Generalizable Retrievers](https://mlsanity.com/paper/2112.07899/) (2021)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking](https://mlsanity.com/paper/2110.07367/) (2021)
- [Improving Passage Retrieval with Zero-Shot Question Generation](https://mlsanity.com/paper/2204.07496/) (2022)
- [Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering](https://mlsanity.com/paper/2307.16877/) (2023)
- [End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering](https://mlsanity.com/paper/2106.05346/) (2021)
- [Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering](https://mlsanity.com/paper/2210.02627/) (2022)
- [UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph](https://mlsanity.com/paper/2212.00959/) (2022)
- [Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering](https://mlsanity.com/paper/2202.13296/) (2022)
- [Dense X Retrieval: What Retrieval Granularity Should We Use?](https://mlsanity.com/paper/2312.06648/) (2023)
- [Adversarial Retriever-Ranker for dense text retrieval](https://mlsanity.com/paper/2110.03611/) (2021)
- [KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering](https://mlsanity.com/paper/2110.04330/) (2021)
- [Domain-matched Pre-training Tasks for Dense Retrieval](https://mlsanity.com/paper/2107.13602/) (2021)
- [Questions Are All You Need to Train a Dense Passage Retriever](https://mlsanity.com/paper/2206.10658/) (2022)
- [Learning to Retrieve Passages without Supervision](https://mlsanity.com/paper/2112.07708/) (2021)
- [Multi-View Document Representation Learning for Open-Domain Dense Retrieval](https://mlsanity.com/paper/2203.08372/) (2022)
- [Hindsight: Posterior-guided training of retrievers for improved open-ended generation](https://mlsanity.com/paper/2110.07752/) (2021)
- [RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards](https://mlsanity.com/paper/2410.13509/) (2024)
- [Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximization](https://mlsanity.com/paper/2405.02816/) (2024)
- [Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval](https://mlsanity.com/paper/2103.11920/) (2021)
- [REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering](https://mlsanity.com/paper/2402.17497/) (2024)
- [PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design](https://mlsanity.com/paper/2403.05676/) (2024)
- [RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing](https://mlsanity.com/paper/2404.19543/) (2024)
- [Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models](https://mlsanity.com/paper/2310.09949/) (2023)
- [Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.00175/) (2024)
- [Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering](https://mlsanity.com/paper/2210.02933/) (2022)
- [PROD: Progressive Distillation for Dense Retrieval](https://mlsanity.com/paper/2209.13335/) (2022)
- [SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval](https://mlsanity.com/paper/2210.11773/) (2022)

## Abstract (arXiv)

Recent work on training neural retrievers for open-domain question answering (OpenQA) has employed both supervised and unsupervised approaches. However, it remains unclear how unsupervised and supervised methods can be used most effectively for neural retrievers. In this work, we systematically study retriever pre-training. We first propose an approach of unsupervised pre-training with the Inverse Cloze Task and masked salient spans, followed by supervised finetuning using question-context pairs. This approach leads to absolute gains of 2+ points over the previous best result in the top-20 retrieval accuracy on Natural Questions and TriviaQA datasets. We also explore two approaches for end-to-end supervised training of the reader and retriever components in OpenQA models. In the first approach, the reader considers each retrieved document separately while in the second approach, the reader considers all the retrieved documents together. Our experiments demonstrate the effectiveness of these approaches as we obtain new state-of-the-art results. On the Natural Questions dataset, we obtain a top-20 retrieval accuracy of 84, an improvement of 5 points over the recent DPR model. In addition, we achieve good results on answer extraction, outperforming recent models like REALM and RAG by 3+ points. We further scale up end-to-end training to large models and show consistent gains in performance over smaller models.