# Adaptive Document Retrieval for Deep Question Answering

arXiv: https://arxiv.org/abs/1808.06528 · HTML: https://mlsanity.com/paper/1808.06528/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2018.

## Built on by (most cited first, 16 of 16)

- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [CoLT5: Faster Long-Range Transformers with Conditional Computation](https://mlsanity.com/paper/2303.09752/) (2023)
- [SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization](https://mlsanity.com/paper/2203.06569/) (2022)
- [Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering](https://mlsanity.com/paper/2109.04014/) (2021)
- [Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment](https://mlsanity.com/paper/2204.03025/) (2022)
- [Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute](https://mlsanity.com/paper/2301.10448/) (2023)
- [Joint Models for Answer Verification in Question Answering Systems](https://mlsanity.com/paper/2107.04217/) (2021)
- [Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?](https://mlsanity.com/paper/2211.12707/) (2022)
- [How Many Tools Should an LLM Agent See? A Chance-Corrected Answer](https://mlsanity.com/paper/2605.24660/) (2026)
- [Weakly-Supervised Open-Retrieval Conversational Question Answering](https://mlsanity.com/paper/2103.02537/) (2021)
- [Double Retrieval and Ranking for Accurate Question Answering](https://mlsanity.com/paper/2201.05981/) (2022)
- [PairReranker: Pairwise Reranking for Natural Language Generation](https://mlsanity.com/paper/2212.10555/) (2022)
- [Data-Augmented and Retrieval-Augmented Context Enrichment in Chinese Media Bias Detection](https://mlsanity.com/paper/2311.01372/) (2023)
- [Multifaceted Improvements for Conversational Open-Domain Question Answering](https://mlsanity.com/paper/2204.00266/) (2022)
- [Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering](https://mlsanity.com/paper/2507.04069/) (2025)
- [Recent Advances in Automated Question Answering In Biomedical Domain](https://mlsanity.com/paper/2111.05937/) (2021)

## Abstract (arXiv)

State-of-the-art systems in deep question answering proceed as follows: (1) an initial document retrieval selects relevant documents, which (2) are then processed by a neural network in order to extract the final answer. Yet the exact interplay between both components is poorly understood, especially concerning the number of candidate documents that should be retrieved. We show that choosing a static number of documents -- as used in prior research -- suffers from a noise-information trade-off and yields suboptimal results. As a remedy, we propose an adaptive document retrieval model. This learns the optimal candidate number for document retrieval, conditional on the size of the corpus and the query. We report extensive experimental results showing that our adaptive approach outperforms state-of-the-art methods on multiple benchmark datasets, as well as in the context of corpora with variable sizes.