# Detect, Retrieve, Comprehend: A Flexible Framework for Zero-Shot Document-Level Question Answering

arXiv: https://arxiv.org/abs/2210.01959 · HTML: https://mlsanity.com/paper/2210.01959/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 4 Oct 2022.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [DiT: Self-supervised Pre-training for Document Image Transformer](https://mlsanity.com/paper/2203.02378/) (2022)
- [VisualMRC: Machine Reading Comprehension on Document Images](https://mlsanity.com/paper/2101.11272/) (2021)
- [Simple Entity-Centric Questions Challenge Dense Retrievers](https://mlsanity.com/paper/2109.08535/) (2021)
- [End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering](https://mlsanity.com/paper/2106.05346/) (2021)
- [Document AI: Benchmarks, Models and Applications](https://mlsanity.com/paper/2111.08609/) (2021)
- [UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training](https://mlsanity.com/paper/2202.12359/) (2022)
- [AxCell: Automatic Extraction of Results from Machine Learning Papers](https://mlsanity.com/paper/2004.14356/) (2020)
- [On Generating Extended Summaries of Long Documents](https://mlsanity.com/paper/2012.14136/) (2020)
- [Talk to Papers: Bringing Neural Question Answering to Academic Search](https://mlsanity.com/paper/2004.02002/) (2020)
- [A New Neural Search and Insights Platform for Navigating and Organizing AI Research](https://mlsanity.com/paper/2011.00061/) (2020)

## Built on by (most cited first, 4 of 4)

- [A Study of Situational Reasoning for Traffic Understanding](https://mlsanity.com/paper/2306.02520/) (2023)
- [DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search](https://mlsanity.com/paper/2602.05014/) (2026)
- [Instant Answering in E-Commerce Buyer-Seller Messaging using Message-to-Question Reformulation](https://mlsanity.com/paper/2401.09785/) (2024)
- [From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation](https://mlsanity.com/paper/2608.30461/) (2026)

## Abstract (arXiv)

Researchers produce thousands of scholarly documents containing valuable technical knowledge. The community faces the laborious task of reading these documents to identify, extract, and synthesize information. To automate information gathering, document-level question answering (QA) offers a flexible framework where human-posed questions can be adapted to extract diverse knowledge. Finetuning QA systems requires access to labeled data (tuples of context, question and answer). However, data curation for document QA is uniquely challenging because the context (i.e. answer evidence passage) needs to be retrieved from potentially long, ill-formatted documents. Existing QA datasets sidestep this challenge by providing short, well-defined contexts that are unrealistic in real-world applications. We present a three-stage document QA approach: (1) text extraction from PDF; (2) evidence retrieval from extracted texts to form well-posed contexts; (3) QA to extract knowledge from contexts to return high-quality answers -- extractive, abstractive, or Boolean. Using QASPER for evaluation, our detect-retrieve-comprehend (DRC) system achieves a +7.19 improvement in Answer-F1 over existing baselines while delivering superior context selection. Our results demonstrate that DRC holds tremendous promise as a flexible framework for practical scientific document QA.