LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation

Summary: LLMLog improves LLM-based log template generation through multi-round active annotation, selecting representative, low-confidence logs and adaptive in-context examples. An edit-distance similarity metric and keyword-covering context selection yield state-of-the-art accuracy across 16 datasets. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 14136
Venue: VLDB
Year: 2025
Pagerank: 5.093636e-05
Overall Rank: 10,909 | 25.16%
DOI: 10.14778/3746405.3746433

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Fei Teng (Hong Kong University of Science and Technology)
2. Haoyang Li (Hong Kong Polytechnic University)
3. Lei Chen (Hong Kong University of Science and Technology)

BibTeX Citation

@article{teng_vldb25,
        title = {{LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation}},
        author = {Teng, Fei and Li, Haoyang and Chen, Lei},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {9},
        pages = {3134--3148},
        doi = {10.14778/3746405.3746433},
        url = {https://doi.org/10.14778/3746405.3746433},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 30 of 30 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
279	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB	0.00022468369
530	An Analytical Study of Large SPARQL Query Logs	2018	VLDB	0.0001709169
1,014	Aether: A Scalable Approach to Logging	2010	VLDB	0.00012650747
1,923	Annotating Columns with Pre-trained Language Models	2022	SIGMOD	9.4789109e-05
2,553	LLM-R^2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency	2025	VLDB	8.4283807e-05
3,088	Query Fresh: Log Shipping on Steroids	2018	VLDB	7.7694381e-05
3,536	How Large Language Models Will Disrupt Data Management	2023	VLDB	7.3297343e-05
4,515	ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models	2024	VLDB	6.6492389e-05
4,621	spade: Synthesizing Data Quality Assertions for Large Language Model Pipelines	2024	VLDB	6.6024412e-05
4,886	Chat2Data: An Interactive Data Analysis System with RAG, Vector Databases and LLMs	2024	VLDB	6.4614955e-05
5,168	How to Build Templates for RDF Question/Answering —An Uncertain Graph Similarity Join Approach	2015	SIGMOD	6.3353772e-05
5,171	An Efficient Transfer Learning Based Configuration Adviser for Database Tuning	2024	VLDB	6.3347618e-05
5,321	High-Performance Row Pattern Recognition Using Joins	2023	VLDB	6.2659937e-05
5,418	Representing Paths in Graph Database Pattern Matching	2023	VLDB	6.2255373e-05
5,506	Accurate and Fast Approximate Graph Pattern Mining at Scale	2025	VLDB	6.1925892e-05
5,969	Maestro: Automatic Generation of Comprehensive Benchmarks for Question Answering Over Knowledge Graphs	2023	SIGMOD	6.0247307e-05
6,101	LLM for Data Management	2024	VLDB	5.9774273e-05
6,575	TencentCLS: The Cloud Log Service with High Query Performances	2022	VLDB	5.8369845e-05
6,995	Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models	2025	VLDB	5.7301567e-05
7,363	Adaptive Log Compression for Massive Log Data	2013	SIGMOD	5.6333834e-05
7,690	Auto-Validate: Unsupervised Data Validation Using Data-Domain Patterns Inferred from Data Lakes	2021	SIGMOD	5.5669307e-05
8,244	SHiFT: An Efficient, Flexible Search Engine for Transfer Learning	2023	VLDB	5.4587712e-05
8,458	RECA: Related Tables Enhanced Column Semantic Type Annotation Framework	2023	VLDB	5.4217059e-05
8,586	A Framework for Privacy Preserving Localized Graph Pattern Query Processing	2023	SIGMOD	5.4073203e-05
10,018	From Logs to Causal Inference: Diagnosing Large Systems	2025	VLDB	5.1757914e-05
10,019	Substructure-aware Log Anomaly Detection	2025	VLDB	5.1757914e-05
10,021	CORAL: Collaborative Automatic Labeling System based on Large Language Models	2024	VLDB	5.1757914e-05
10,022	HSAP: A Human-in-the-loop Social Media-based Situation Awareness Platform	2024	VLDB	5.1757914e-05
10,023	A Universal Question-Answering Platform for Knowledge Graphs	2023	SIGMOD	5.1757914e-05
10,024	Near-Duplicate Sequence Search at Scale for Large Language Model Memorization Evaluation	2023	SIGMOD	5.1757914e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,019	Substructure-aware Log Anomaly Detection	2025	VLDB
2	713	Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes	2024	VLDB
3	10,733	ScaleLLM: A Technique for Scalable LLM-augmented Data Systems	2025	SIGMOD
4	10,614	LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning	2026	VLDB
5	8,829	Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees	2026	SIGMOD
6	10,318	In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration	2026	SIGMOD
7	10,956	CoLA: Model Collaboration for Log-based Anomaly Detection	2025	VLDB
8	6,101	LLM for Data Management	2024	VLDB
9	3,376	Robust and Transferable Log-based Anomaly Detection	2023	SIGMOD
10	5,713	PreLog: A Pre-trained Model for Log Analytics	2024	SIGMOD