Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Journal of Technology Informatics and Engineering
Zoe Zhao
Computer Science, UCSD, CA, USA
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Cost-Aware LLM-Style Routing for AIOps Log Analysis: Log Parsing, Anomaly Detection, Fault Diagnosis, and Incident Summarization on LogEval Task Files Chenyu Li; Ge Liu; Zoe Zhao
Journal of Technology Informatics and Engineering Vol. 5 No. 2 (2026): AUGUST | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v5i2.538

Abstract

This study investigates a local and cost-aware routing framework for AIOps log analysis using the LogEval benchmark. The evaluation covers four tasks: log parsing, anomaly detection, fault diagnosis, and incident summarization. Instead of relying on external large language model APIs, the experiment implements deterministic local policies that simulate zero-shot and few-shot LLM-style inference under controlled token-cost and latency assumptions. Six approaches were compared: regex normalization, TF-IDF with machine learning, a local character-based classifier, zero-shot policy, few-shot retrieval policy, and a routing cascade. At a risk threshold of 0.20, the router directed only 12.9% of queries to the few-shot retrieval policy while achieving parsing accuracy of 0.991, anomaly F1-score of 1.000, diagnosis accuracy of 1.000, ROUGE-L of 0.743, and BLEU-1 of 0.814. The routing strategy reduced simulated token cost by 80.1% compared with always using few-shot retrieval. Additional unseen-template evaluation revealed limited generalization for closed-label classifiers and retrieval methods when encountering unseen patterns. The findings indicate that routing can effectively reduce AIOps inference costs, while further validation with real LLMs and stronger generalization testing are required before production deployment.
Co-Authors Chenyu Li Ge Liu