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

arXiv: https://arxiv.org/abs/2606.28076 · HTML: https://mlsanity.com/paper/2606.28076/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text](https://mlsanity.com/paper/1904.09537/) (2019)
- [Variational Reasoning for Question Answering with Knowledge Graph](https://mlsanity.com/paper/1709.04071/) (2017)
- [Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals](https://mlsanity.com/paper/2101.03737/) (2021)
- [KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph](https://mlsanity.com/paper/2402.11163/) (2024)
- [TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph](https://mlsanity.com/paper/2104.07302/) (2021)
- [Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models](https://mlsanity.com/paper/2410.13080/) (2024)
- [Multimodal Reasoning with Multimodal Knowledge Graph](https://mlsanity.com/paper/2406.02030/) (2024)
- [LargeEA: Aligning Entities for Large-scale Knowledge Graphs](https://mlsanity.com/paper/2108.05211/) (2021)
- [Towards Ontology Construction with Language Models](https://mlsanity.com/paper/2309.09898/) (2023)
- [ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph](https://mlsanity.com/paper/2401.00158/) (2023)
- [Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering](https://mlsanity.com/paper/2502.11491/) (2025)
- [Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA](https://mlsanity.com/paper/2311.07850/) (2023)
- [Generations of Knowledge Graphs: The Crazy Ideas and the Business Impact](https://mlsanity.com/paper/2308.14217/) (2023)
- [SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2502.03283/) (2025)
- [Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection](https://mlsanity.com/paper/2502.14932/) (2025)
- [Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering](https://mlsanity.com/paper/2502.03992/) (2025)

## 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.