Metraipolis › archive › dc_e142df73bd79

APOLO: Automatic Prompt Optimization for Ontology Learning — arXiv:2609.34540

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34540
License (as archived): CC0-1.0
Archived: 2026-10-07T20:57:52.234Z
SHA-256 of the archived text: 77555a7ed531c70a056e340732f9511ad5d8f8e0465b78f9f0d6e1d515bd79be
Stable URL of this page: https://metraipolis.com/documento/dc_e142df73bd79

How to cite

APOLO: Automatic Prompt Optimization for Ontology Learning — arXiv:2609.34540 — arXiv (en), https://arxiv.org/abs/2609.34540 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e142df73bd79 (Metraipolis archive dc_e142df73bd79, sha256 77555a7ed531c70a056e340732f9511ad5d8f8e0465b78f9f0d6e1d515bd79be)

BibTeX

@misc{dce142df73bd79,
  title = {APOLO: Automatic Prompt Optimization for Ontology Learning — arXiv:2609.34540},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34540},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e142df73bd79; sha256 77555a7ed531c70a056e340732f9511ad5d8f8e0465b78f9f0d6e1d515bd79be},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34540. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34540 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:01.576Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).