Relational Graph Convolutional Neural Networks for Multihop Reasoning: A Comparative Study
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
Abstract (arXiv)
Multihop Question Answering is a complex Natural Language Processing task that requires multiple steps of reasoning to find the correct answer to a given question. Previous research has explored the use of models based on Graph Neural Networks for tackling this task. Various architectures have been proposed, including Relational Graph Convolutional Networks (RGCN). For these many node types and relations between them have been introduced, such as simple entity co-occurrences, modelling coreferences, or "reasoning paths" from questions to answers via intermediary entities. Nevertheless, a thoughtful analysis on which relations, node types, embeddings and architecture are the most beneficial for this task is still missing. In this paper we explore a number of RGCN-based Multihop QA models, graph relations, and node embeddings, and empirically explore the influence of each on Multihop QA performance on the WikiHop dataset.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 22 of its 25 references that are in the map. First posted on arXiv 12 Oct 2022.
Builds on
22 of 25 references.
References · 22
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2017Graph Attention Networkscited by 8,923
- 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2020Longformer: The Long-Document Transformercited by 3,413
- 2018Deep contextualized word representationscited by 2,290
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
- 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 754
- 2017Constructing Datasets for Multi-hop Reading Comprehension Across Documentscited by 190
10 more
- 2019Compositional Questions Do Not Necessitate Multi-hop Reasoningcited by 88
- 2019Hierarchical Graph Network for Multi-hop Question Answeringcited by 83
- 2020RealFormer: Transformer Likes Residual Attentioncited by 62
- 2018Question Answering by Reasoning Across Documents with Graph Convolutional Networkscited by 56
- 2019Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphscited by 53
- 2020Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?cited by 30
- 2020A Simple Yet Strong Pipeline for HotpotQAcited by 24
- 2019BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answeringcited by 19
- 2020HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questionscited by 19
- 2020Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Networkcited by 9
Built on by
Citing papers per year: 2024: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2022QAGCN: Answering Multi-Relation Questions via Single-Step Implicit Reasoning over Knowledge Graphs
- 2022Relation-Aware Language-Graph Transformer for Question Answering
- 2022TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs
- 2023Graph Reasoning for Question Answering with Triplet Retrieval
- 2025Multimodal Multihop Source Retrieval for Web Question Answering
- 2026Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
- 2022From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answering
- 2025Efficient Multi-Hop Question Answering over Knowledge Graphs via LLM Planning and Embedding-Guided Search