LLM-Assisted Logic Rule Learning: Scaling Human Expertise for Time Series Anomaly Detection
This addresses the challenge of scaling expert analysis for anomaly detection in supply chains, offering a practical solution for operational settings, though it is incremental by combining LLMs with rule-based methods.
The paper tackled the problem of time series anomaly detection in supply chain management by proposing a framework that uses large language models (LLMs) to encode human expertise into interpretable logic rules, resulting in outperforming unsupervised methods in accuracy and interpretability while providing consistent, low-latency results.
Time series anomaly detection is critical for supply chain management to take proactive operations, but faces challenges: classical unsupervised anomaly detection based on exploiting data patterns often yields results misaligned with business requirements and domain knowledge, while manual expert analysis cannot scale to millions of products in the supply chain. We propose a framework that leverages large language models (LLMs) to systematically encode human expertise into interpretable, logic-based rules for detecting anomaly patterns in supply chain time series data. Our approach operates in three stages: 1) LLM-based labeling of training data instructed by domain knowledge, 2) automated generation and iterative improvements of symbolic rules through LLM-driven optimization, and 3) rule augmentation with business-relevant anomaly categories supported by LLMs to enhance interpretability. The experiment results showcase that our approach outperforms the unsupervised learning methods in both detection accuracy and interpretability. Furthermore, compared to direct LLM deployment for time series anomaly detection, our approach provides consistent, deterministic results with low computational latency and cost, making it ideal for production deployment. The proposed framework thus demonstrates how LLMs can bridge the gap between scalable automation and expert-driven decision-making in operational settings.