Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models

TL;DR

This study explores how GPT-4, combined with a structured knowledge base, can improve metadata standard adherence for datasets, showing significant gains when domain information is provided, thus aiding automated metadata curation.

Contribution

The paper demonstrates that integrating GPT-4 with a structured knowledge base significantly enhances metadata standard adherence, especially with domain-specific information, advancing automated curation methods.

Findings

GPT-4 alone marginally improved adherence from 79% to 80%.

Providing domain information increased adherence to 97%.

Structured knowledge bases enhance LLMs' metadata curation capabilities.

Abstract

Metadata play a crucial role in ensuring the findability, accessibility, interoperability, and reusability of datasets. This paper investigates the potential of large language models (LLMs), specifically GPT-4, to improve adherence to metadata standards. We conducted experiments on 200 random data records describing human samples relating to lung cancer from the NCBI BioSample repository, evaluating GPT-4's ability to suggest edits for adherence to metadata standards. We computed the adherence accuracy of field name-field value pairs through a peer review process, and we observed a marginal average improvement in adherence to the standard data dictionary from 79% to 80% (p<0.5). We then prompted GPT-4 with domain information in the form of the textual descriptions of CEDAR templates and recorded a significant improvement to 97% from 79% (p<0.01). These results indicate that, while LLMs may not be able to correct legacy metadata to ensure satisfactory adherence to standards when unaided, they do show promise for use in automated metadata curation when integrated with a structured knowledge base