# Did We Miss Something Important? Studying and Exploring Variable-Aware Log Abstraction

arXiv: https://arxiv.org/abs/2304.11391 · HTML: https://mlsanity.com/paper/2304.11391/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2023.

## Built on by (most cited first, 19 of 19)

- [Interpretable Online Log Analysis Using Large Language Models with Prompt Strategies](https://mlsanity.com/paper/2308.07610/) (2023)
- [LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing](https://mlsanity.com/paper/2404.18001/) (2024)
- [NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations](https://mlsanity.com/paper/2406.19783/) (2024)
- [LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models](https://mlsanity.com/paper/2408.13727/) (2024)
- [Log Parsing: How Far Can ChatGPT Go?](https://mlsanity.com/paper/2306.01590/) (2023)
- [LogLM: From Task-based to Instruction-based Automated Log Analysis](https://mlsanity.com/paper/2410.09352/) (2024)
- [Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge](https://mlsanity.com/paper/2412.01377/) (2024)
- [Log Anomaly Detection with Large Language Models via Knowledge-Enriched Fusion](https://mlsanity.com/paper/2512.11997/) (2025)
- [Demystifying and Extracting Fault-indicating Information from Logs for Failure Diagnosis](https://mlsanity.com/paper/2409.13561/) (2024)
- [Log Parsing using LLMs with Self-Generated In-Context Learning and Self-Correction](https://mlsanity.com/paper/2406.03376/) (2024)
- [LibreLog: Accurate and Efficient Unsupervised Log Parsing Using Open-Source Large Language Models](https://mlsanity.com/paper/2408.01585/) (2024)
- [System Log Parsing with Large Language Models: A Review](https://mlsanity.com/paper/2504.04877/) (2025)
- [SDLog: A Deep Learning Framework for Detecting Sensitive Information in Software Logs](https://mlsanity.com/paper/2505.14976/) (2025)
- [Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs](https://mlsanity.com/paper/2604.20211/) (2026)
- [LogBabylon: A Unified Framework for Cross-Log File Integration and Analysis](https://mlsanity.com/paper/2412.12364/) (2024)
- [SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements](https://mlsanity.com/paper/2607.27409/) (2026)
- [Semi-supervised learning via DQN for log anomaly detection](https://mlsanity.com/paper/2401.03151/) (2024)
- [A Word is Worth 4-bit: Efficient Log Parsing with Binary Coded Decimal Recognition](https://mlsanity.com/paper/2506.01147/) (2025)
- [SCOPE: Tree-based Self-Correcting Online Log Parsing via Syntactic-Semantic Collaboration](https://mlsanity.com/paper/2603.27247/) (2026)

## Abstract (arXiv)

Due to the sheer size of software logs, developers rely on automated techniques for log analysis. One of the first and most important steps of automated log analysis is log abstraction, which parses the raw logs into a structured format. Prior log abstraction techniques aim to identify and abstract all the dynamic variables in logs and output a static log template for automated log analysis. However, these abstracted dynamic variables may also contain important information that is useful to different tasks in log analysis. In this paper, we investigate the characteristics of dynamic variables and their importance in practice, and explore the potential of a variable-aware log abstraction technique. Through manual investigations and surveys with practitioners, we find that different categories of dynamic variables record various information that can be important depending on the given tasks, the distinction of dynamic variables in log abstraction can further assist in log analysis. We then propose a deep learning based log abstraction approach, named VALB, which can identify different categories of dynamic variables and preserve the value of specified categories of dynamic variables along with the log templates (i.e., variable-aware log abstraction). Through the evaluation on a widely used log abstraction benchmark, we find that VALB outperforms other state-of-the-art log abstraction techniques on general log abstraction (i.e., when abstracting all the dynamic variables) and also achieves a high variable-aware log abstraction accuracy that further identifies the category of the dynamic variables. Our study highlights the potential of leveraging the important information recorded in the dynamic variables to further improve the process of log analysis.