# APOLO: Automatic Prompt Optimization for Ontology Learning

arXiv: https://arxiv.org/abs/2609.34540 · HTML: https://mlsanity.com/paper/2609.34540/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [From human experts to machines: An LLM supported approach to ontology and knowledge graph construction](https://mlsanity.com/paper/2403.08345/) (2024)
- [Devstral: Fine-tuning Language Models for Coding Agent Applications](https://mlsanity.com/paper/2509.25193/) (2025)
- [Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study](https://mlsanity.com/paper/2506.19773/) (2025)

## Abstract (arXiv)

Ontology Learning (OL) from text has advanced with the emergence of Large Language Models (LLMs), but it remains challenging due to the limited availability of annotated training data and the difficulty of adapting LLMs to perform OL effectively. We address this via APOLO - Automatic Prompt Optimization for Ontology Learning, by casting OL as an explicit prompt optimization problem over LLM modules. To obtain training data, we employ a multi-agent system that generates text-ontology pairs from existing expert-curated ontologies. We then propose two ontology learner architectures: a greedy and an autoregressive learner, and optimize both using GEPA, a greedy evolutionary prompt optimizer built on DSPy. Experiments on two ontologies - a biomedical (DOID) and a plant ontology (PO) show consistent improvements after optimization across nearly all model and mode combinations, with autoregressive learners achieving the largest gains. Our results demonstrate that prompt optimization is a viable and lightweight alternative to fine-tuning for OL, and that the autoregressive formulation better captures ontological structure than the greedy approach.