Published September 3, 2024 | Version v1.0
Software Open

Replication package for "A Comparative Study on Large Language Models for Log Parsing"

  • 1. ROR icon Simula Research Laboratory
  • 2. ROR icon BI Norwegian Business School

Description

This repository contains the replication package for the paper:

"A Comparative Study on Large Language Models for Log Parsing"
Merve Astekin, Max Hort, and Leon Moonen
Accepted for the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM '24)

The paper is deposited on arXiv, will be available at the publisher's site, and a preprint is included in this repository.

The replication package is archived on Zenodo with DOI: 10.5281/zenodo.13625383. The source code is distributed under the MIT license, the data is distributed under the CC BY 4.0 license.

Organization

The repository is organized as follows:

  • Data in the data folder, with a dedicated README.

  • Archived source code in the src folder, with a dedicated README.

  • Archived scripts in the ollama_scripts folder, with a dedicated README.

  • Analysis of the results in the analysis folder, with a dedicated README.

  • The file requirements.txt in the root contains the frozen requirements for the Python environment used at the time of running the experiments.

Citation

If you build on this data or code, please cite this work by referring to the paper:

@inproceedings{astekin2024:comparative,
   title = {A Comparative Study on Large Language Models for Log Parsing},
   author = {Merve Astekin and Max Hort and Leon Moonen},
   booktitle = {Proceedings of 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM’24)},
   year = {2024},
   publisher = {ACM},
   doi = {https://doi.org/10.1145/3674805.3686684}
}

Files

Large Language Models for Log Parsing.zip

Files (3.2 MB)

Name Size Download all
md5:b554b0aa1af90333a5d2dc6e302239fb
3.2 MB Preview Download

Additional details

Funding

The Research Council of Norway
cureIT - Adaptive Immunity for Software: Making Systems and Services Autonomously Self-Healing 300461
The Research Council of Norway
secureIT - Reducing Digital Vulnerabilities by Providing Software Engineers with Intelligent Automated Software Security Assessment Technology 288787
European Commission
condenSE - Sustainable Training of Code Language Models through Data Refinement 101151798
The Research Council of Norway
eX3 - Experimental Infrastructure for Exploration of Exascale Computing 270053

Dates

Created
2024-09-01