# Hierarchical Graph Network for Multi-hop Question Answering

arXiv: https://arxiv.org/abs/1911.03631 · HTML: https://mlsanity.com/paper/1911.03631/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2019.

## Built on by (most cited first, 30 of 83)

- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing](https://mlsanity.com/paper/2301.07507/) (2023)
- [TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph](https://mlsanity.com/paper/2104.07302/) (2021)
- [Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text](https://mlsanity.com/paper/2105.03659/) (2021)
- [Reasoning Like Program Executors](https://mlsanity.com/paper/2201.11473/) (2022)
- [JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering](https://mlsanity.com/paper/2112.02732/) (2021)
- [End-to-End Beam Retrieval for Multi-Hop Question Answering](https://mlsanity.com/paper/2308.08973/) (2023)
- [HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs](https://mlsanity.com/paper/2406.06027/) (2024)
- [Causal Reasoning of Entities and Events in Procedural Texts](https://mlsanity.com/paper/2301.10896/) (2023)
- [Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks](https://mlsanity.com/paper/2302.11050/) (2023)
- [ReasonBERT: Pre-trained to Reason with Distant Supervision](https://mlsanity.com/paper/2109.04912/) (2021)
- [Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation](https://mlsanity.com/paper/2104.07555/) (2021)
- [Chain-of-Skills: A Configurable Model for Open-domain Question Answering](https://mlsanity.com/paper/2305.03130/) (2023)
- [PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation](https://mlsanity.com/paper/2501.11551/) (2025)
- [Efficient Graph Deep Learning in TensorFlow with tf_geometric](https://mlsanity.com/paper/2101.11552/) (2021)
- [Exploiting Reasoning Chains for Multi-hop Science Question Answering](https://mlsanity.com/paper/2109.02905/) (2021)
- [Robustifying Multi-hop QA through Pseudo-Evidentiality Training](https://mlsanity.com/paper/2107.03242/) (2021)
- [Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy](https://mlsanity.com/paper/2107.11823/) (2021)
- [From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering](https://mlsanity.com/paper/2205.11729/) (2022)
- [Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering](https://mlsanity.com/paper/2206.08486/) (2022)
- [Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization](https://mlsanity.com/paper/2103.12235/) (2021)
- [Iterative Hierarchical Attention for Answering Complex Questions over Long Documents](https://mlsanity.com/paper/2106.00200/) (2021)
- [Reasoning over Hybrid Chain for Table-and-Text Open Domain QA](https://mlsanity.com/paper/2201.05880/) (2022)
- [Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling](https://mlsanity.com/paper/2210.10369/) (2022)
- [Box Embeddings: An open-source library for representation learning using geometric structures](https://mlsanity.com/paper/2109.04997/) (2021)
- [Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction](https://mlsanity.com/paper/2302.02601/) (2023)
- [Lost-in-Distance: Impact of Contextual Proximity on LLM Performance in Graph Tasks](https://mlsanity.com/paper/2410.01985/) (2024)
- [Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoning](https://mlsanity.com/paper/2210.07138/) (2022)

## Abstract (arXiv)

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical graph is created by constructing nodes on different levels of granularity (questions, paragraphs, sentences, entities), the representations of which are initialized with pre-trained contextual encoders. Given this hierarchical graph, the initial node representations are updated through graph propagation, and multi-hop reasoning is performed via traversing through the graph edges for each subsequent sub-task (e.g., paragraph selection, supporting facts extraction, answer prediction). By weaving heterogeneous nodes into an integral unified graph, this hierarchical differentiation of node granularity enables HGN to support different question answering sub-tasks simultaneously. Experiments on the HotpotQA benchmark demonstrate that the proposed model achieves new state of the art, outperforming existing multi-hop QA approaches.