KG-First, LLM-Fallback: A Hybrid Microservice for Grounded Skill Search and Explanation

TL;DR

This paper presents SkillGraph-Service, a hybrid microservice that unifies competency frameworks into a Knowledge Graph, combining symbolic and sub-symbolic methods for effective skill search and explanation with high efficiency.

Contribution

It introduces a KG-first, LLM-fallback architecture with a hybrid retrieval engine and constrained LLM explanations, improving skill data integration for education and labor market alignment.

Findings

Achieves superior retrieval effectiveness with nDCG@5 > 0.94 and sub-200 ms latency.

Hybrid retrieval reduces reliance on expensive cross-encoder re-ranking.

JSON-constrained LLMs provide high citation precision, while templates maximize evidence coverage.

Abstract

Authoritative competency frameworks such as ESCO, ROME, and O*NET are essential for aligning education with labor market needs, yet their technical complexity and structural heterogeneity hinder practical adoption by educators. This paper introduces SkillGraph-Service, an interoperable microservice designed to bridge this gap by unifying these resources into a provenance-preserving Knowledge Graph (KG). Adopting a KG-first, LLM-fallback architecture, the system combines symbolic rigor with sub-symbolic flexibility. It implements a lightweight hybrid retrieval engine (fusing SQLite FTS5 and HNSW vector search) to handle the vocabulary mismatch in educator queries, and utilizes Large Language Models (LLMs) strictly for constrained ranking and audience-aware explanation. Empirical evaluation on a multilingual dataset reveals that the proposed hybrid strategy achieves superior retrieval effectiveness (nDCG@5>0.94) with sub-200 ms latency, rendering computationally expensive cross-encoder re-ranking may be unnecessary for this domain. Furthermore, an analysis of generated explanations highlights a trade-off between fluency and faithfulness: while JSON-constrained LLMs ensure high citation precision, deterministic templates remain the most reliable method for maximizing evidence coverage. The resulting architecture offers a practical, scalable, and auditable solution for integrating complex skill data into digital learning ecosystems.