Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering
Quick Answer
The OPI framework enhances multi-hop knowledge graph question answering by using an ontology-guided approach, improving Hit@1/F1 scores by 4.6/5.0 on WebQSP and 8.9/3.3 on CWQ.
Quick Take
The OPI framework enhances multi-hop knowledge graph question answering by using an ontology-guided approach, improving Hit@1/F1 scores by 4.6/5.0 on WebQSP and 8.9/3.3 on CWQ. This method effectively reduces search space and filters irrelevant evidence, leading to more reliable answers.
Key Points
- OPI introduces a relation-centric ontology graph to manage type constraints.
- Bidirectional retrieval combines topic-side expansion with answer-side matching.
- Iterative refinement filters out irrelevant evidence for better answer predictions.
- Experiments show significant performance improvements over prior methods.
- Achieves near-saturated Hit@1 on MetaQA with the retrieval module alone.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 28076v1 Announce Type: new Abstract: 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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Verification Horizon: No Silver Bullet for Coding Agent Rewards
As coding agents evolve, verifying solutions becomes more challenging than generating them, necessitating a focus on scalable, faithful, and robust verification methods. The study reveals that no fixed reward function can sustain effectiveness as model capabilities advance, emphasizing the need for verification to evolve alongside solution generation.