DBScholar

Back to papers

PreLog: A Pre-trained Model for Log Analytics

Summary: PreLog: foundation model for log analytics, pre-trained on unlabeled heterogeneous logs with log-specific entry/sequence objectives to capture semantics/structure. Prompt tuning casts downstream parsing and anomaly detection into the pretraining format, yielding unified, cost-effective transfer across tasks. (summarized by gpt-5.4-mini on May 24 2026)

Paper ID
6989
Venue
SIGMOD
Year
2024
Pagerank
6.1123632e-05
Overall Rank
5,713 | 60.81%
DOI
10.1145/3654966

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{le_sigmod24,
        title = {{PreLog: A Pre-trained Model for Log Analytics}},
        author = {Le, Van-Hoang and Zhang, Hongyu},
        series = {{SIGMOD} '24},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3654966},
        url = {https://dl.acm.org/doi/10.1145/3654966},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank Citing Paper Year Venue Pagerank
10,194 ANTEATER: A Filter-then-Scrutinize Architecture for End-to-End Attack Investigation 2026 SIGMOD 5.093636e-05
10,507 Unseen Anomaly Detection from System Logs 2026 SIGMOD 5.093636e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 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