LLMCrater：基于大语言模型的生命周期感知型FAIR元数据生成框架
LLMCrater: Lifecycle-Aware FAIR Metadata Generation using Large Language Models
浏览论文内容
中文总结 AI 辅助
该研究提出生命周期感知型元数据生成框架LLMCrater，结合LLMs与RO-Crate元数据概要，在科研生命周期四阶段逐步生成符合规范的元数据，经两个用例验证可生成有效RO-Crate。
中文摘要 AI 辅助
FAIR（可发现、可访问、可互操作和可重用）元数据对于科研资源的发现、互操作和重用至关重要。然而，创建和维护FAIR元数据在很大程度上仍依赖人工，这使得科研生命周期中产生的各类科研制品的相关过程耗时较长。现有方法主要在发表阶段生成元数据，错失了捕获逐步产生的上下文信息的机会。为解决这一局限，本文提出LLMCrater，一种生命周期感知型元数据生成框架，将大语言模型（LLMs）与特定阶段的RO-Crate元数据概要相结合。该框架在科研生命周期的四个阶段（设计、开发、部署、执行与溯源）逐步丰富元数据，同时兼容RO-Crate 1.1和欧洲云基础设施（EOSC）元数据建议。它可自动从异构制品中提取元数据，生成并验证机器可操作的RO-Crate，支持向FAIR知识库和持久标识符（PID）服务（如Zenodo）发布。我们通过两个代表性用例验证该方法：SLICES-RI内的5G实验环境，以及GreenDIGIT的EcoJupyter平台上的实验。结果表明，LLMCrater在整个科研生命周期中逐步丰富元数据，生成符合RO-Crate 1.1规范的有效RO-Crate。
英文摘要
FAIR (Findable, Accessible, Interoperable, and Reusable) metadata is essential for the discovery, interoperability, and reuse of scientific research assets. However, creating and maintaining FAIR metadata remains largely manual, making the process time-consuming for heterogeneous research artifacts generated throughout the research lifecycle. Existing approaches primarily generate metadata at publication time, missing opportunities to capture contextual information as it becomes available. To address this limitation, we present \emph{LLMCrater}, a lifecycle-aware metadata generation framework that combines Large Language Models (LLMs) with stage-specific RO-Crate metadata profiles. The framework progressively enriches metadata across four research lifecycle stages (Design, Development, Deployment, and Execution \& Provenance) while remaining compatible with RO-Crate~1.1 and EOSC metadata recommendations. It automatically extracts metadata from heterogeneous artifacts, generates and validates machine-actionable RO-Crates, and supports publication to FAIR repositories and PID services (e.g., Zenodo). We demonstrate the approach using two representative use cases: a 5G experimentation environment within SLICES-RI and an experiment on GreenDIGIT's EcoJupyter platform. Results show that LLMCrater progressively enriches metadata throughout the research lifecycle and generates valid RO-Crates conforming to the RO-Crate~1.1 specification.
