Large Language Models for Anomaly Detection in Computational Workflows: from Supervised Fine-Tuning to In-Context Learning

2024/07/24 by Hongwei Jin, Jin, Hongwei, George Papadimitriou +12 · 5 citations
Computer Science · Decision Sciences · #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Network Security and Intrusion Detection #Scientific Computing and Data Management #Software Engineering (cs.SE)

paper · pdf · doi:10.48550/arxiv.2407.17545

openalex publication_date 2024/07/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

Anomaly detection in computational workflows is critical for ensuring system reliability and security. However, traditional rule-based methods struggle to detect novel anomalies. This paper leverages large language models (LLMs) for workflow anomaly detection by exploiting their ability to learn complex data patterns. Two approaches are investigated: 1) supervised fine-tuning (SFT), where pre-trained LLMs are fine-tuned on labeled data for sentence classification to identify anomalies, and 2) in-context learning (ICL) where prompts containing task descriptions and examples guide LLMs in few-shot anomaly detection without fine-tuning. The paper evaluates the performance, efficiency, generalization of SFT models, and explores zero-shot and few-shot ICL prompts and interpretability enhancement via chain-of-thought prompting. Experiments across multiple workflow datasets demonstrate the promising potential of LLMs for effective anomaly detection in complex executions.

Cited by

• Mamba4Net: Distilled Hybrid Mamba Large Language Models For Networking
• SPEAR: Soft Prompt Enhanced Anomaly Recognition for Time Series Data
• K⁴: Online Log Anomaly Detection Via Unsupervised Typicality Learning
• InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching
• A Survey of AIOps in the Era of Large Language Models

Related

• ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models
• Synergizing Large Language Models and Task-specific Models for Time Series Anomaly Detection
• AD-LLM: Benchmarking Large Language Models for Anomaly Detection
• Mechanistic Anomaly Detection for "Quirky" Language Models
• Anomaly Detection of Tabular Data Using LLMs