# Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent

arXiv: https://arxiv.org/abs/2604.08552 · HTML: https://mlsanity.com/paper/2604.08552/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 13 of 13)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning](https://mlsanity.com/paper/2304.02711/) (2023)
- [Generalizable and Scalable Multistage Biomedical Concept Normalization Leveraging Large Language Models](https://mlsanity.com/paper/2405.15122/) (2024)
- [Modeling community standards for metadata as templates makes data FAIR](https://mlsanity.com/paper/2208.02836/) (2022)
- [The variable quality of metadata about biological samples used in biomedical experiments](https://mlsanity.com/paper/1808.06907/) (2018)
- [The CEDAR Workbench: An Ontology-Assisted Environment for Authoring Metadata that Describe Scientific Experiments](https://mlsanity.com/paper/1905.06480/) (2019)
- [Predicting Failures of LLMs to Link Biomedical Ontology Terms to Identifiers Evidence Across Models and Ontologies](https://mlsanity.com/paper/2509.04458/) (2025)
- [Ensuring Adherence to Standards in Experiment-Related Metadata Entered Via Spreadsheets](https://mlsanity.com/paper/2409.08897/) (2024)
- [Toward Total Recall: Enhancing FAIRness through AI-Driven Metadata Standardization](https://mlsanity.com/paper/2504.05307/) (2025)
- [Knowledge engineering for open science: Building and deploying knowledge bases for metadata standards](https://mlsanity.com/paper/2507.22391/) (2025)

## Built on by (most cited first, 1 of 1)

- [Label Agreement Does Not Measure Authorization](https://mlsanity.com/paper/2610.04544/) (2026)

## Abstract (arXiv)

Descriptive scientific metadata in public repositories are often incomplete and inconsistent with community standards and ontologies, limiting data FAIRness. Large language models (LLMs) offer a promising approach to automatically standardizing such metadata when the LLM is provided with knowledge of the relevant standards in machine-actionable form (e.g., as metadata templates from systems such as the CEDAR Workbench). 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-augmented LLM agent that retrieves complete CEDAR metadata templates and dynamically queries authoritative biomedical terminology services at execution time. We compared ARMS with a prompt-based approach on 839 legacy metadata records from the Human BioMolecular Atlas Program (HuBMAP), using expert-standardized records as the reference standard. ARMS outperformed the prompt-based approach, 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.