Papers by Kuofei Fang
Beyond Topology: Generative Node Importance Estimation via Structure-Guided Semantic Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for estimating node importance are limited and rely on topological aggregation. |
| Approach: | They propose a generative reasoning framework that leverages Large Language Models to generate precise importance scores for entities in Knowledge Graphs. |
| Outcome: | Extensive experiments show that the proposed framework outperforms existing methods and is generalized across domains. |