Surprising Effectiveness of Self-Demonstrations in Enhancing Schema-Ontology Mapping with LLMs

2026-09-12

AI Summary

本文提出一种结合神经-符号任务分解与自动生成模式引导演示的方法，有效解决了使用大型语言模型进行数据库模式到本体映射时的挑战。

Abstract

Integrating heterogeneous relational databases into a centralized ontology remains a persistent challenge in enterprise knowledge representation, primarily due to semantic heterogeneity, cryptic schema naming, missing metadata, and the abstraction gap between relational schemas and ontological models. Although large language models (LLMs) offer strong semantic reasoning capabilities, we show that directly applying them through one-shot prompting or naive multi-stage pipelines leads to poor performance for schema-ontology mapping. This paper presents a self-demonstration-driven approach that combines a neuro-symbolic task decomposition with a novel mechanism for automatically generating pattern-guided, dependency-aware demonstrations to address this integration challenge. Our approach incorporates two key strategies to achieve substantial accuracy gains over existing LLM-based schema integration methods: (i) a neuro-symbolic decomposition of the task into cascaded sub-tasks, where symbolic constraints structure the search space and LLMs perform semantic reasoning within each focused sub-task, and (ii) self-generated demonstrations guided by domain-agnostic patterns to supervise each sub-task. Experiments on three of the most challenging scenarios from the RODI benchmark show that our approach achieves state-of-the-art performance, substantially outperforming (25 percentage points F1 improvements) both traditional schema-to-ontology mapping techniques and recent LLM-based schema-to-ontology and schema matching approaches. Ablation studies further reveal the significant benefits of pattern-guided self-demonstrations and the complementary benefits of neuro-symbolic task decomposition.

Problem

• heterogeneous relational databases
• centralized ontology
• semantic heterogeneity
• schema-ontology mapping

Innovation

• self-demonstration
• neuro-symbolic task decomposition
• pattern-guided
• dependency-aware
• schema-ontology mapping