CoLA: Model Collaboration for Log-based Anomaly Detection
Summary: CoLA couples an efficient small detector with an LLM expert: the detector filters logs, while the LLM verifies anomalies, explains decisions, and refines the detector. Evaluated on three real datasets, it improves accuracy, efficiency, explainability, and labor cost. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Xuhang Zhu (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang University)
- 2. Xiu Tang (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang University)
- 3. Sai Wu (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang University)
- 4. Jichen Li (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang University)
- 5. Haobo Wang (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang University)
- 6. Chang Yao (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang University)
- 7. Quanqing Xu (Ant Financial)
- 8. Gang Chen (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang University)
BibTeX Citation
@article{zhu_vldb25,
title = {{CoLA: Model Collaboration for Log-based Anomaly Detection}},
author = {Zhu, Xuhang and Tang, Xiu and Wu, Sai and Li, Jichen and Wang, Haobo and Yao, Chang and Xu, Quanqing and Chen, Gang},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {3979--3987},
doi = {10.14778/3749646.3749668},
url = {https://doi.org/10.14778/3749646.3749668},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,507 | Unseen Anomaly Detection from System Logs | 2026 | SIGMOD |
| 2 | 5,354 | Can Large Language Models Predict Data Correlations from Column Names? | 2023 | VLDB |
| 3 | 10,298 | The Power of Anomaly Detection in Predictive Maintenance: [Experiments & Analysis] | 2026 | SIGMOD |
| 4 | 1,920 | D-Bot: Database Diagnosis System using Large Language Models | 2024 | VLDB |
| 5 | 10,733 | ScaleLLM: A Technique for Scalable LLM-augmented Data Systems | 2025 | SIGMOD |
| 6 | 5,713 | PreLog: A Pre-trained Model for Log Analytics | 2024 | SIGMOD |
| 7 | 10,019 | Substructure-aware Log Anomaly Detection | 2025 | VLDB |
| 8 | 10,021 | CORAL: Collaborative Automatic Labeling System based on Large Language Models | 2024 | VLDB |
| 9 | 10,909 | LLMLog: Advanced Log Template Generation via LLM-driven Multi-Round Annotation | 2025 | VLDB |
| 10 | 3,376 | Robust and Transferable Log-based Anomaly Detection | 2023 | SIGMOD |