# Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

arXiv: https://arxiv.org/abs/1906.04618 · HTML: https://mlsanity.com/paper/1906.04618/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2019.

## Built on by (most cited first, 15 of 15)

- [A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods](https://mlsanity.com/paper/2204.03508/) (2022)
- [Joint Models for Answer Verification in Question Answering Systems](https://mlsanity.com/paper/2107.04217/) (2021)
- [Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases](https://mlsanity.com/paper/2502.20317/) (2025)
- [Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization](https://mlsanity.com/paper/2103.12235/) (2021)
- [AnswerQuest: A System for Generating Question-Answer Items from Multi-Paragraph Documents](https://mlsanity.com/paper/2103.03820/) (2021)
- [Double Retrieval and Ranking for Accurate Question Answering](https://mlsanity.com/paper/2201.05981/) (2022)
- [Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE](https://mlsanity.com/paper/2509.03626/) (2025)
- [ReFIT: Relevance Feedback from a Reranker during Inference](https://mlsanity.com/paper/2305.11744/) (2023)
- [Strong and Efficient Baselines for Open Domain Conversational Question Answering](https://mlsanity.com/paper/2310.14708/) (2023)
- [CRAFT: Training-Free Cascaded Retrieval for Tabular QA](https://mlsanity.com/paper/2505.14984/) (2025)
- [The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims](https://mlsanity.com/paper/2411.14072/) (2024)
- [Multi Document Reading Comprehension](https://mlsanity.com/paper/2201.01706/) (2022)
- [An Understanding-Oriented Robust Machine Reading Comprehension Model](https://mlsanity.com/paper/2207.00187/) (2022)
- [Clinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization](https://mlsanity.com/paper/2407.14000/) (2024)
- [Embedding Inference Attack](https://mlsanity.com/paper/2607.01276/) (2026)

## Abstract (arXiv)

This paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can improve the overall performance. However, the pipeline system is inefficient since the input is re-encoded within each module, and is unable to leverage upstream components to help downstream training. In this work, we present RE3QA, a unified question answering model that combines context retrieving, reading comprehension, and answer reranking to predict the final answer. Unlike previous pipelined approaches, RE3QA shares contextualized text representation across different components, and is carefully designed to use high-quality upstream outputs (e.g., retrieved context or candidate answers) for directly supervising downstream modules (e.g., the reader or the reranker). As a result, the whole network can be trained end-to-end to avoid the context inconsistency problem. Experiments show that our model outperforms the pipelined baseline and achieves state-of-the-art results on two versions of TriviaQA and two variants of SQuAD.