{"slug": "ontology-guided-evidence-path-inference-for-multi-hop-knowledge-graph-question", "title": "Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering", "summary": "Researchers propose OPI, an ontology-guided evidence path inference framework for multi-hop knowledge graph question answering, which reduces search space and improves accuracy by using a relation-centric ontology graph and bidirectional retrieval. Experiments show OPI outperforms prior methods on WebQSP, CWQ, and MetaQA benchmarks.", "body_md": "arXiv:2606.28076v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/ontology-guided-evidence-path-inference-for-multi-hop-knowledge-graph-question", "canonical_source": "https://arxiv.org/abs/2606.28076", "published_at": "2026-06-29 04:00:00+00:00", "updated_at": "2026-06-29 04:11:49.186026+00:00", "lang": "en", "topics": ["machine-learning", "natural-language-processing", "ai-research"], "entities": ["OPI", "WebQSP", "CWQ", "MetaQA"], "alternates": {"html": "https://wpnews.pro/news/ontology-guided-evidence-path-inference-for-multi-hop-knowledge-graph-question", "markdown": "https://wpnews.pro/news/ontology-guided-evidence-path-inference-for-multi-hop-knowledge-graph-question.md", "text": "https://wpnews.pro/news/ontology-guided-evidence-path-inference-for-multi-hop-knowledge-graph-question.txt", "jsonld": "https://wpnews.pro/news/ontology-guided-evidence-path-inference-for-multi-hop-knowledge-graph-question.jsonld"}}