mlsanityData to 7 Oct 2026

Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering

arXiv 2606.28076 ↗First posted 26 Jun 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Knowledge graph question answering (KGQA) aims to answer natural-language questions by reasoning over structured facts. Existing multi-hop KGQA methods mainly rely on topic-centered expansion, which faces two key challenges: the search space rapidly grows with noisy mixed-type paths, and retrieved paths may fail to satisfy the semantic constraints of complex questions. To address these challenges, we propose OPI, an ontology-guided evidence path inference framework for multi-hop KGQA. OPI introduces a relation-centric ontology graph to capture the head-tail type constraints of relations, providing a compact interface for answer-side constraints. Based on this ontology graph, OPI first introduces a bidirectional retrieval mechanism by mapping the predicted answer type to compatible final-hop relations and combining topic-side prefix expansion with answer-side final-hop matching, thereby suppressing noisy mixed-type expansion. OPI further adopts an iterative refinement strategy to reassess retrieved paths and candidate answers under the question context, filtering type-compatible but question-irrelevant evidence for more reliable answer prediction. Experiments on WebQSP, CWQ, and MetaQA show that OPI substantially reduces the search space, improves Hit@1/F1 by 4.6/5.0 points on WebQSP and 8.9/3.3 points on CWQ over the strongest prior results, and achieves near-saturated Hit@1 on MetaQA with the retrieval module alone.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 42 references that are in the map. First posted on arXiv 26 Jun 2026.

Builds on

21 of 42 references.

References · 21

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  3. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  4. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  5. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  6. 2019PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Textcited by 182
  7. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  8. 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
  9. 2024KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graphcited by 90
  10. 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
  11. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Modelscited by 47
  12. 2024Multimodal Reasoning with Multimodal Knowledge Graphcited by 43
9 more
  1. 2021LargeEA: Aligning Entities for Large-scale Knowledge Graphscited by 26
  2. 2023Towards Ontology Construction with Language Modelscited by 23
  3. 2023ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graphcited by 23
  4. 2025Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answeringcited by 15
  5. 2023Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQAcited by 11
  6. 2023Generations of Knowledge Graphs: The Crazy Ideas and the Business Impactcited by 10
  7. 2025SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphscited by 10
  8. 2025Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflectioncited by 6
  9. 2025Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answeringcited by 3

Built on by

Not cited yet.