# Automated Skill Decomposition Meets Expert Ontologies: Bridging the Granularity Gap with LLMs

arXiv: https://arxiv.org/abs/2510.11313 · HTML: https://mlsanity.com/paper/2510.11313/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Ontology Generation using Large Language Models](https://mlsanity.com/paper/2503.05388/) (2025)
- [How Well Do LLMs Predict Prerequisite Skills? Zero-Shot Comparison to Expert-Defined Concepts](https://mlsanity.com/paper/2507.18479/) (2025)
- [Vers un cadre ontologique pour la gestion des comp'etences : `a des fins de formation, de recrutement, de m'etier, ou de recherches associ'ees](https://mlsanity.com/paper/2507.05767/) (2025)

## Built on by (most cited first, 4 of 4)

- [When Can We Trust Early Warnings? Leakage-Excluded Early Outcome Prediction from LMS Interaction Logs](https://mlsanity.com/paper/2605.25794/) (2026)
- [Development of Ontological Knowledge Bases by Leveraging Large Language Models](https://mlsanity.com/paper/2601.10436/) (2026)
- [KG-First, LLM-Fallback: A Hybrid Microservice for Grounded Skill Search and Explanation](https://mlsanity.com/paper/2605.01582/) (2026)
- [From Learning Resources to Competencies: LLM-Based Tagging with Evidence and Graph Constraints](https://mlsanity.com/paper/2605.28483/) (2026)

## Abstract (arXiv)

This paper investigates automated skill decomposition using Large Language Models (LLMs) and proposes a rigorous, ontology-grounded evaluation framework. Our framework standardizes the pipeline from prompting and generation to normalization and alignment with ontology nodes. To evaluate outputs, we introduce two metrics: a semantic F1-score that uses optimal embedding-based matching to assess content accuracy, and a hierarchy-aware F1-score that credits structurally correct placements to assess granularity. We conduct experiments on ROME-ESCO-DecompSkill, a curated subset of parents, comparing two prompting strategies: zero-shot and leakage-safe few-shot with exemplars. Across diverse LLMs, zero-shot offers a strong baseline, while few-shot consistently stabilizes phrasing and granularity and improves hierarchy-aware alignment. A latency analysis further shows that exemplar-guided prompts are competitive - and sometimes faster - than unguided zero-shot due to more schema-compliant completions. Together, the framework, benchmark, and metrics provide a reproducible foundation for developing ontology-faithful skill decomposition systems.