Automated Archival Descriptions with Federated Intelligence of LLMs

2025-04-08

AI Summary

Standardizing archival description and automatically generating high-quality metadata remain challenging due to domain complexity and linguistic ambiguity. Method: This paper proposes a multi-large language model (LLM) collaborative intelligent agent system. It introduces a novel federated LLM optimization framework integrating intelligent agent architecture, domain-specific prompt engineering, multi-model collaborative reasoning, and output consistency verification—ensuring both syntactic compliance and semantic fidelity. Contribution/Results: The approach overcomes inherent limitations of single-LLM systems in archival metadata generation, enabling structured adherence to international standards such as ISAD(G). Experiments on a real-world, multi-format archival dataset demonstrate statistically significant improvements in metadata quality, accuracy, and reliability over single-model baselines. The system provides a scalable, standards-compliant technical pathway for archival digitization and semantic enrichment.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Enforcing archival standards requires specialized expertise, and manually creating metadata descriptions for archival materials is a tedious and error-prone task. This work aims at exploring the potential of agentic AI and large language models (LLMs) in addressing the challenges of implementing a standardized archival description process. To this end, we introduce an agentic AI-driven system for automated generation of high-quality metadata descriptions of archival materials. We develop a federated optimization approach that unites the intelligence of multiple LLMs to construct optimal archival metadata. We also suggest methods to overcome the challenges associated with using LLMs for consistent metadata generation. To evaluate the feasibility and effectiveness of our techniques, we conducted extensive experiments using a real-world dataset of archival materials, which covers a variety of document types and data formats. The evaluation results demonstrate the feasibility of our techniques and highlight the superior performance of the federated optimization approach compared to single-model solutions in metadata quality and reliability.

Problem

• Automating archival metadata generation using AI to reduce manual effort
• Improving metadata quality via federated optimization of multiple LLMs
• Ensuring consistency in archival standards with agentic AI systems

Innovation

• Agentic AI-driven automated metadata generation
• Federated optimization uniting multiple LLMs
• Methods for consistent LLM metadata generation