arXiv cs.AI· Josef Hardi, Martin J. O'Connor, Marcos Martinez-Romero, Jean G. Rosario, Stephen A. Fisher, Mark A. Musen·· 14 小时前AI 评分29
ARMS：用本体约束的 LLM 智能体自动标准化遗留生物医学元数据
Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent
AI 导读
ARMS 是一个在运行时检索完整 CEDAR 元数据模板并动态查询权威生物医学术语服务的工具型 LLM 智能体，在 839 条遗留元数据记录上把标准化精度从 0.56 提升到 0.93、召回率从 0.51 提升到 0.85。本体约束字段的增益最大，精度由 0.36 升至 0.92，优于仅靠提示词注入标准的固定快照方案。
正文 · 原文
Abstract:Descriptive scientific metadata in public repositories are often incomplete and inconsistent with community standards and ontologies, limiting data FAIRness. Large language models (LLM) offer a promising approach to automatically standardizing such metadata when the LLM is provided with knowledge of the relevant standards in machine-actionable form. Entry of metadata standards through prompt engineering offers only fixed snapshots of the relevant standards, however, and it relies on an LLM's pretrained knowledge to interpret and satisfy constraints related to the standard. We evaluate whether giving an LLM access to metadata specifications and authoritative terminology at runtime improves automated metadata standardization. We present ARMS, a tool-using LLM agent that retrieves complete CEDAR metadata templates and that queries authoritative biomedical terminology services dynamically at execution time. We compared ARMS with a prompt-engineering approach on 839 legacy metadata records describing experiment datasets with expert-standardized records serving as the reference standard. Across the corpus, ARMS outperformed the prompt-engineering approach in converting legacy metadata to standards-compliant form, increasing precision from 0.56 to 0.93 and recall from 0.51 to 0.85, with improvements across all field categories and assay types. The largest gains occurred for ontology-constrained fields where precision increased from 0.36 to 0.92. Our findings show that access to appropriate metadata standards can substantially improve LLM-based standardization of legacy metadata. ARMS improves metadata standardization by giving LLMs runtime access to the authoritative resources that define valid metadata. Representation of metadata standards in machine-actionable form enhances the task of rectifying legacy metadata using LLM technology, especially when those standards can be queried dynamically.
| Subjects: | Databases (cs.DB); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2604.08552 [cs.DB] |
| (or arXiv:2604.08552v5 [cs.DB] for this version) | |
| https://doi.org/10.48550/arXiv.2604.08552 arXiv-issued DOI via DataCite |
|
| Journal reference: | Journal of Biomedical Informatics 184 (2026) 105116 |
| Related DOI: | https://doi.org/10.1016/j.jbi.2026.105116
DOI(s) linking to related resources |
Submission history
From: Josef Hardi [view email]
[v1]
Tue, 10 Mar 2026 18:47:30 UTC (529 KB)
[v2]
Thu, 18 Jun 2026 17:56:13 UTC (960 KB)
[v3]
Wed, 2 Sep 2026 04:27:03 UTC (585 KB)
[v4]
Tue, 13 Oct 2026 18:58:21 UTC (2,616 KB)
[v5]
Mon, 26 Oct 2026 16:33:02 UTC (2,616 KB)
来源：arXiv cs.AI · arxiv.org