LLM-SrcLog: Towards Proactive and Unified Log Template Extraction via Large Language Models Article Swipe

MAKE IMPACT

Jiaqi Sun , Wei Li , Cheng Ding , Shiyou Qian , Jianliang Cao · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2512.04474

Log parsing transforms raw logs into structured templates containing constants and variables. It underpins anomaly detection, failure diagnosis, and other AIOps tasks. Current parsers are mostly reactive and log-centric. They only infer templates from logs, mostly overlooking the source code. This restricts their capacity to grasp dynamic log structures or adjust to evolving systems. Moreover, per-log LLM inference is too costly for practical deployment. In this paper, we propose LLM-SrcLog, a proactive and unified framework for log template parsing. It extracts templates directly from source code prior to deployment and supplements them with data-driven parsing for logs without available code. LLM-SrcLog integrates a cross-function static code analyzer to reconstruct meaningful logging contexts, an LLM-based white-box template extractor with post-processing to distinguish constants from variables, and a black-box template extractor that incorporates data-driven clustering for remaining unmatched logs. Experiments on two public benchmarks (Hadoop and Zookeeper) and a large-scale industrial system (Sunfire-Compute) show that, compared to two LLM-based baselines, LLM-SrcLog improves average F1-score by 2-17% and 8-35%. Meanwhile, its online parsing latency is comparable to data-driven methods and about 1,000 times faster than per-log LLM parsing. LLM-SrcLog achieves a near-ideal balance between speed and accuracy. Finally, we further validate the effectiveness of LLM-SrcLog through practical case studies in a real-world production environment.

Type

preprint

Landing Page

http://arxiv.org/abs/2512.04474

PDF

https://arxiv.org/pdf/2512.04474

OA Status

green

OpenAlex ID

https://openalex.org/W4417086746

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4417086746

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2512.04474

Digital Object Identifier

Title

LLM-SrcLog: Towards Proactive and Unified Log Template Extraction via Large Language Models

Work title

Type

preprint

OpenAlex work type

Publication year

2025

Year of publication

Publication date

2025-12-04

Full publication date if available

Authors

Jiaqi Sun, Wei Li, Cheng Ding, Shiyou Qian, Jianliang Cao

List of authors in order

Landing page

https://arxiv.org/abs/2512.04474

Publisher landing page

PDF URL

https://arxiv.org/pdf/2512.04474

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2512.04474

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload