# Self-Supervised Log Parsing

arXiv: https://arxiv.org/abs/2003.07905 · HTML: https://mlsanity.com/paper/2003.07905/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2020.

## Built on by (most cited first, 23 of 23)

- [LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing](https://mlsanity.com/paper/2404.18001/) (2024)
- [Log Parsing: How Far Can ChatGPT Go?](https://mlsanity.com/paper/2306.01590/) (2023)
- [Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging](https://mlsanity.com/paper/2402.18205/) (2024)
- [AI for IT Operations (AIOps) on Cloud Platforms: Reviews, Opportunities and Challenges](https://mlsanity.com/paper/2304.04661/) (2023)
- [Robust and Transferable Anomaly Detection in Log Data using Pre-Trained Language Models](https://mlsanity.com/paper/2102.11570/) (2021)
- [A2Log: Attentive Augmented Log Anomaly Detection](https://mlsanity.com/paper/2109.09537/) (2021)
- [Decentralized Federated Learning Preserves Model and Data Privacy](https://mlsanity.com/paper/2102.00880/) (2021)
- [Reducing Events to Augment Log-based Anomaly Detection Models: An Empirical Study](https://mlsanity.com/paper/2409.04834/) (2024)
- [Artificial Intelligence for IT Operations (AIOPS) Workshop White Paper](https://mlsanity.com/paper/2101.06054/) (2021)
- [A Taxonomy of Anomalies in Log Data](https://mlsanity.com/paper/2111.13462/) (2021)
- [ECLIPSE: Semantic Entropy-LCS for Cross-Lingual Industrial Log Parsing](https://mlsanity.com/paper/2405.13548/) (2024)
- [A Comparative Study on Large Language Models for Log Parsing](https://mlsanity.com/paper/2409.02474/) (2024)
- [Multi-Source Anomaly Detection in Distributed IT Systems](https://mlsanity.com/paper/2101.04977/) (2021)
- [System Log Parsing with Large Language Models: A Review](https://mlsanity.com/paper/2504.04877/) (2025)
- [LUK: Empowering Log Understanding with Expert Knowledge from Large Language Models](https://mlsanity.com/paper/2409.01909/) (2024)
- [Interactive Log Parsing via Light-weight User Feedback](https://mlsanity.com/paper/2301.12225/) (2023)
- [USTEP: Structuration des logs en flux grace `a un arbre de recherche 'evolutif](https://mlsanity.com/paper/2304.12331/) (2023)
- [Progressing from Anomaly Detection to Automated Log Labeling and Pioneering Root Cause Analysis](https://mlsanity.com/paper/2312.14748/) (2023)
- [A Word is Worth 4-bit: Efficient Log Parsing with Binary Coded Decimal Recognition](https://mlsanity.com/paper/2506.01147/) (2025)
- [On Sequence-to-Sequence Models for Automated Log Parsing](https://mlsanity.com/paper/2602.07698/) (2026)
- [TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond](https://mlsanity.com/paper/2605.06906/) (2026)
- [NLLog: Lightweight, Explainable SOC Anomaly Detection via Log-to-Language Rewriting](https://mlsanity.com/paper/2606.04957/) (2026)
- [SpikeLogBERT: Energy-Efficient Log Parsing Using Spiking Transformer Networks](https://mlsanity.com/paper/2606.31781/) (2026)

## Abstract (arXiv)

Logs are extensively used during the development and maintenance of software systems. They collect runtime events and allow tracking of code execution, which enables a variety of critical tasks such as troubleshooting and fault detection. However, large-scale software systems generate massive volumes of semi-structured log records, posing a major challenge for automated analysis. Parsing semi-structured records with free-form text log messages into structured templates is the first and crucial step that enables further analysis. Existing approaches rely on log-specific heuristics or manual rule extraction. These are often specialized in parsing certain log types, and thus, limit performance scores and generalization. We propose a novel parsing technique called NuLog that utilizes a self-supervised learning model and formulates the parsing task as masked language modeling (MLM). In the process of parsing, the model extracts summarizations from the logs in the form of a vector embedding. This allows the coupling of the MLM as pre-training with a downstream anomaly detection task. We evaluate the parsing performance of NuLog on 10 real-world log datasets and compare the results with 12 parsing techniques. The results show that NuLog outperforms existing methods in parsing accuracy with an average of 99% and achieves the lowest edit distance to the ground truth templates. Additionally, two case studies are conducted to demonstrate the ability of the approach for log-based anomaly detection in both supervised and unsupervised scenario. The results show that NuLog can be successfully used to support troubleshooting tasks. The implementation is available at https://github.com/nulog/nulog.