EUVIMEDEUVIMED entdecken
Crossref

Scalable and Efficient Large-Scale Log Analysis with LLMs: An IT Software Support Case Study

Pranjal Gupta, Karan Bhukar, Harshit Kumar, Seema Nagar, Prateeti Mohapatra, Debanjana Kar

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 39958-39967

DOI: 10.1609/aaai.v40i47.41430 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Pranjal Gupta und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

IT environments typically have logging mechanisms to monitor system health and detect issues. However, the huge volume of generated logs makes manual inspection impractical, highlighting the importance of automated log analysis in IT Software Support. In this paper, we propose a log analytics tool that leverages Large Language Models (LLMs) for log data processing and issue diagnosis, enabling the generation of automated insights and summaries. We further present a novel approach for efficiently running LLMs on CPUs to process massive log volumes in minimal time without compromising output quality. We share the insights and lessons learned from deployment of the tool - in production since March 2024 - scaled across 70 software products, processing over 2000 tickets for issue diagnosis, achieving a time savings of 300+ man hours and an estimated $15,444 per month in manpower costs compared to the traditional practices.

Zitieren

APA

Gupta, P., Bhukar, K., Kumar, H., Nagar, S., Mohapatra, P., & Kar, D. (2026). Scalable and Efficient Large-Scale Log Analysis with LLMs: An IT Software Support Case Study. Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39958-39967. https://doi.org/10.1609/aaai.v40i47.41430

Vancouver

Gupta P, Bhukar K, Kumar H, Nagar S, Mohapatra P, Kar D. Scalable and Efficient Large-Scale Log Analysis with LLMs: An IT Software Support Case Study. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):39958-39967. doi:10.1609/aaai.v40i47.41430

BibTeX
@article{Gupta2026,
  author = {Gupta, Pranjal and Bhukar, Karan and Kumar, Harshit and Nagar, Seema and Mohapatra, Prateeti and Kar, Debanjana},
  title = {Scalable and Efficient Large-Scale Log Analysis with LLMs: An IT Software Support Case Study},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {47},
  pages = {39958--39967},
  doi = {10.1609/aaai.v40i47.41430}
}
Kostenlos starten →