LogSyn: A Few-Shot LLM Framework for Structured Insight Extraction from Unstructured General Aviation Maintenance Logs
This work addresses the underuse of safety data in aviation maintenance logs for improving workflows and predictive analytics, though it is incremental as it applies existing LLM methods to a new domain-specific dataset.
The paper tackles the problem of extracting structured insights from unstructured general aviation maintenance logs by introducing LogSyn, a few-shot LLM framework that converts logs into machine-readable data, achieving results on 6,169 records through Controlled Abstraction Generation to summarize narratives and classify events.
Aircraft maintenance logs hold valuable safety data but remain underused due to their unstructured text format. This paper introduces LogSyn, a framework that uses Large Language Models (LLMs) to convert these logs into structured, machine-readable data. Using few-shot in-context learning on 6,169 records, LogSyn performs Controlled Abstraction Generation (CAG) to summarize problem-resolution narratives and classify events within a detailed hierarchical ontology. The framework identifies key failure patterns, offering a scalable method for semantic structuring and actionable insight extraction from maintenance logs. This work provides a practical path to improve maintenance workflows and predictive analytics in aviation and related industries.