# Dense Hierarchical Retrieval for Open-Domain Question Answering

arXiv: https://arxiv.org/abs/2110.15439 · HTML: https://mlsanity.com/paper/2110.15439/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2021.

## Built on by (most cited first, 30 of 34)

- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval](https://mlsanity.com/paper/2411.12644/) (2024)
- [NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes](https://mlsanity.com/paper/2504.11544/) (2025)
- [Modeling Multi-hop Question Answering as Single Sequence Prediction](https://mlsanity.com/paper/2205.09226/) (2022)
- [Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis](https://mlsanity.com/paper/2505.21700/) (2025)
- [Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database](https://mlsanity.com/paper/2211.05165/) (2022)
- [Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems](https://mlsanity.com/paper/2505.18366/) (2025)
- [Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering](https://mlsanity.com/paper/2506.06313/) (2025)
- [Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables](https://mlsanity.com/paper/2309.11049/) (2023)
- [HPE:Answering Complex Questions over Text by Hybrid Question Parsing and Execution](https://mlsanity.com/paper/2305.07789/) (2023)
- [CoRank: LLM-Based Compact Reranking with Document Features for Scientific Retrieval](https://mlsanity.com/paper/2505.13757/) (2025)
- [Slot Induction via Pre-trained Language Model Probing and Multi-level Contrastive Learning](https://mlsanity.com/paper/2308.04712/) (2023)
- [Graph-based Alignment and Uniformity for Recommendation](https://mlsanity.com/paper/2308.09292/) (2023)
- [CORI: CJKV Benchmark with Romanization Integration -- A step towards Cross-lingual Transfer Beyond Textual Scripts](https://mlsanity.com/paper/2404.12618/) (2024)
- [Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism](https://mlsanity.com/paper/2410.12859/) (2024)
- [Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering](https://mlsanity.com/paper/2510.24402/) (2025)
- [DTCRS: Dynamic Tree Construction for Recursive Summarization](https://mlsanity.com/paper/2604.07012/) (2026)
- [AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation](https://mlsanity.com/paper/2212.08841/) (2022)
- [When to Read Documents or QA History: On Unified and Selective Open-domain QA](https://mlsanity.com/paper/2306.04176/) (2023)
- [Telco-DPR: A Hybrid Dataset for Evaluating Retrieval Models of 3GPP Technical Specifications](https://mlsanity.com/paper/2410.19790/) (2024)
- [Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering](https://mlsanity.com/paper/2306.15905/) (2023)
- [Seg2Act: Global Context-aware Action Generation for Document Logical Structuring](https://mlsanity.com/paper/2410.06802/) (2024)
- [QuOTE: Question-Oriented Text Embeddings](https://mlsanity.com/paper/2502.10976/) (2025)
- [MFBE: Leveraging Multi-Field Information of FAQs for Efficient Dense Retrieval](https://mlsanity.com/paper/2302.11953/) (2023)
- [Modeling Uncertainty and Using Post-fusion as Fallback Improves Retrieval Augmented Generation with LLMs](https://mlsanity.com/paper/2308.12574/) (2023)
- [GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation](https://mlsanity.com/paper/2409.15566/) (2024)
- [PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA](https://mlsanity.com/paper/2410.04790/) (2024)
- [GeAR: Generation Augmented Retrieval](https://mlsanity.com/paper/2501.02772/) (2025)
- [RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations](https://mlsanity.com/paper/2602.22013/) (2026)
- [Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.00529/) (2026)

## Abstract (arXiv)

Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval process. However, current dense retrievers require splitting documents into short passages that usually contain local, partial, and sometimes biased context, and highly depend on the splitting process. As a consequence, it may yield inaccurate and misleading hidden representations, thus deteriorating the final retrieval result. In this work, we propose Dense Hierarchical Retrieval (DHR), a hierarchical framework that can generate accurate dense representations of passages by utilizing both macroscopic semantics in the document and microscopic semantics specific to each passage. Specifically, a document-level retriever first identifies relevant documents, among which relevant passages are then retrieved by a passage-level retriever. The ranking of the retrieved passages will be further calibrated by examining the document-level relevance. In addition, hierarchical title structure and two negative sampling strategies (i.e., In-Doc and In-Sec negatives) are investigated. We apply DHR to large-scale open-domain QA datasets. DHR significantly outperforms the original dense passage retriever and helps an end-to-end QA system outperform the strong baselines on multiple open-domain QA benchmarks.