# HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions

arXiv: https://arxiv.org/abs/2012.15534 · HTML: https://mlsanity.com/paper/2012.15534/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2020.

## Built on by (most cited first, 19 of 19)

- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [Adaptive Information Seeking for Open-Domain Question Answering](https://mlsanity.com/paper/2109.06747/) (2021)
- [Modeling Multi-hop Question Answering as Single Sequence Prediction](https://mlsanity.com/paper/2205.09226/) (2022)
- [Few-shot Reranking for Multi-hop QA via Language Model Prompting](https://mlsanity.com/paper/2205.12650/) (2022)
- [Chain-of-Skills: A Configurable Model for Open-domain Question Answering](https://mlsanity.com/paper/2305.03130/) (2023)
- [Natural Logic-guided Autoregressive Multi-hop Document Retrieval for Fact Verification](https://mlsanity.com/paper/2212.05276/) (2022)
- [MIRAGE: A Metric-Intensive Benchmark for Retrieval-Augmented Generation Evaluation](https://mlsanity.com/paper/2504.17137/) (2025)
- [Iterative Hierarchical Attention for Answering Complex Questions over Long Documents](https://mlsanity.com/paper/2106.00200/) (2021)
- [Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning](https://mlsanity.com/paper/2210.07138/) (2022)
- [Single Sequence Prediction over Reasoning Graphs for Multi-hop QA](https://mlsanity.com/paper/2307.00335/) (2023)
- [Performance Prediction for Multi-hop Questions](https://mlsanity.com/paper/2308.06431/) (2023)
- [Weakly Supervised Pre-Training for Multi-Hop Retriever](https://mlsanity.com/paper/2106.09983/) (2021)
- [Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning](https://mlsanity.com/paper/2505.17086/) (2025)
- [EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension](https://mlsanity.com/paper/2108.07994/) (2021)
- [Retrieval from Within: An Intrinsic Capability of Attention-Based Models](https://mlsanity.com/paper/2605.05806/) (2026)
- [Relational Graph Convolutional Neural Networks for Multihop Reasoning: A Comparative Study](https://mlsanity.com/paper/2210.06418/) (2022)
- [Momentum Posterior Regularization for Multi-hop Dense Retrieval](https://mlsanity.com/paper/2502.20399/) (2024)
- [Gradually Excavating External Knowledge for Implicit Complex Question Answering](https://mlsanity.com/paper/2603.08148/) (2026)

## Abstract (arXiv)

Collecting supporting evidence from large corpora of text (e.g., Wikipedia) is of great challenge for open-domain Question Answering (QA). Especially, for multi-hop open-domain QA, scattered evidence pieces are required to be gathered together to support the answer extraction. In this paper, we propose a new retrieval target, hop, to collect the hidden reasoning evidence from Wikipedia for complex question answering. Specifically, the hop in this paper is defined as the combination of a hyperlink and the corresponding outbound link document. The hyperlink is encoded as the mention embedding which models the structured knowledge of how the outbound link entity is mentioned in the textual context, and the corresponding outbound link document is encoded as the document embedding representing the unstructured knowledge within it. Accordingly, we build HopRetriever which retrieves hops over Wikipedia to answer complex questions. Experiments on the HotpotQA dataset demonstrate that HopRetriever outperforms previously published evidence retrieval methods by large margins. Moreover, our approach also yields quantifiable interpretations of the evidence collection process.