MicLog: Towards Accurate and Efficient LLM-based Log Parsing via Progressive Meta In-Context Learning
Jianbo Yu, Yixuan Li, Hai Xu, Kang Xu, Junjielong Xu, Zhijing Li, Pinjia He, Wanyuan Wang
Abstract
Log parsing converts semi-structured logs into structured templates, forming a critical foundation for downstream analysis. Traditional syntax and semantic-based parsers often struggle with semantic variations in evolving logs and data scarcity stemming from their limited domain coverage. Recent large language model (LLM)-based parsers leverage in-context learning (ICL) to extract semantics from examples, demonstrating superior accuracy. However, LLM-based parsers face two main challenges: 1) underutilization of ICL capabilities, particularly in dynamic example selection and cross-domain generalization, leading to inconsistent performance; 2) time-consuming and costly LLM querying. To address these challenges, we present MicLog, the first progressive meta in-context learning (ProgMeta-ICL) log parsing framework that combines meta-learning with ICL on small open-source LLMs (i.e., Qwen-2.5-3B). Specifically, MicLog: i) enhances LLMs
BibTeX
@inproceedings{aaai2026_miclogtowardsacc,
title = {MicLog: Towards Accurate and Efficient LLM-based Log Parsing via Progressive Meta In-Context Learning},
author = {Jianbo Yu and Yixuan Li and Hai Xu and Kang Xu and Junjielong Xu and Zhijing Li and Pinjia He and Wanyuan Wang},
booktitle = {AAAI 2026},
year = {2026}
}