arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.34540cs.AI

APOLO:用于本体学习的自动提示优化

APOLO: Automatic Prompt Optimization for Ontology Learning

  • Bosch Center for Artificial Intelligence(博世人工智能中心)
  • Bosch Research North America(博世北美研究院)
  • University of Mannheim(曼海姆大学)
  • University of Würzburg(维尔茨堡大学)

机构由 AI 辅助整理,请以论文原文为准。

Huu Tan Mai, Roman Kochnev, Cuong Xuan Chu, Lukas Lange, Heiko Paulheim, Daria Stepanova

AI总结:

本文提出APOLO,将本体学习转化为提示优化问题,利用多智能体生成训练数据,并采用贪婪与自回归两种学习器,经GEPA优化后在生物医学和植物本体上均获提升,证明提示优化是微调的轻量级替代方案。

AI中文摘要:

随着大型语言模型(LLMs)的出现,从文本中进行本体学习(OL)取得了进展,但由于注释训练数据的有限可用性以及使LLMs有效适应本体学习的困难,它仍然具有挑战性。我们通过APOLO——用于本体学习的自动提示优化——来解决这一问题,将本体学习明确地表述为对LLM模块的提示优化问题。为了获取训练数据,我们采用了一个多智能体系统,从现有的专家策展本体中生成文本-本体对。然后,我们提出了两种本体学习器架构:一种贪婪学习器和一种自回归学习器,并使用GEPA(一种基于DSPy构建的贪婪进化提示优化器)对两者进行优化。在两个本体——一个生物医学本体(DOID)和一个植物本体(PO)——上的实验表明,在几乎所有模型和模式组合中,优化后均取得了一致的改进,其中自回归学习器获得了最大的提升。我们的结果表明,提示优化是微调的一种可行且轻量级的替代方案,适用于本体学习,并且自回归公式比贪婪方法更好地捕捉了本体结构。

英文摘要:

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.

补充信息

↑