LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Logs are important in modern software development with runtime information. Log parsing is the first step in many log-based analyses, that involve extracting structured information from unstructured log data. Traditional log parsers face challenges in accurately parsing logs due to the diversity of log formats, which directly impacts the performance of downstream log-analysis tasks. In this paper, we explore the potential of using Large Language Models (LLMs) for log parsing and propose LLMParser, an LLM-based log parser based on generative LLMs and few-shot tuning. We leverage four LLMs, Flan-T5-small, Flan-T5-base, LLaMA-7B, and ChatGLM-6B in LLMParsers. Our evaluation of 16 open-source systems shows that LLMParser achieves statistically significantly higher parsing accuracy than state-of-the-art parsers (a 96% average parsing accuracy). We further conduct a comprehensive empirical analysis on the effect of training size, model size, and pre-training LLM on log parsing accuracy. We find that smaller LLMs may be more effective than more complex LLMs; for instance where Flan-T5-base achieves comparable results as LLaMA-7B with a shorter inference time. We also find that using LLMs pre-trained using logs from other systems does not always improve parsing accuracy. While using pre-trained Flan-T5-base shows an improvement in accuracy, pre-trained LLaMA results in a decrease (decrease by almost 55% in group accuracy). In short, our study provides empirical evidence for using LLMs for log parsing and highlights the limitations and future research direction of LLM-based log parsers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453 · cited 2×
“However, future studies should consider the trade-off between more complex LLMs and higher fine-tuning and inference costs.”
BackgroundInfluentialSelf-citationLLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441
Making Pre-trained Language Models Better Few-shot Learners
Gao, T., Fisch, A., & Chen, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.295 · Cited by 1,380
Drain: an online log parsing approach with fixed depth tree
He, P., Zhu, J., Zheng, Z., & Lyu, M. R. (2017) · 2017 IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws.2017.13 · Cited by 943 · cited 7×
“Prior studies [21, 55] also suggest that increasing the diversity of training data is effective in improving the understanding and generalization ability of deep learning models.”
BackgroundMethodInfluentialA Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., & Schmidt, D. C. (2023) · arXiv · doi:10.48550/arxiv.2302.11382 · Cited by 838
Robust log-based anomaly detection on unstable log data
Zhang, X., Xu, Y., Lin, Q., Qiao, B., Zhang, H., Dang, Y., Xie, C., Yang, X., Cheng, Q., Li, Z., et al. (2019) · Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3338906.3338931 · Cited by 761 · cited 1×
“To assist with log analysis, researchers have proposed many automated approaches for various tasks such as anomaly detection [26, 72], monitoring [5, 63], and root cause analysis [25, 43, 67].”
MethodFantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity
Lu, Y., Bartolo, M., Moore, A., Riedel, S., & Stenetorp, P. (2021) · arXiv · doi:10.48550/arxiv.2104.08786 · Cited by 615 · cited 1×
“Below, we present our few-shot sampling algorithm, LLM selection, prompt selection, and fine-tuning process.”
MethodTools and benchmarks for automated log parsing
Zhu, J., He, S., Liu, J., He, P., Xie, Q., Zheng, Z., & Lyu, M. R. (2019) · 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip.2019.00021 · Cited by 574
Cited by
Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilities
Ferrag, M. A., Alwahedi, F., Battah, A., Cherif, B., Mechri, A., Tihanyi, N., Bisztray, T., & Debbah, M. (2025) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2025.01.001 · Cited by 148
Generative AI for self-adaptive systems: State of the art and research roadmap
Li, J., Zhang, M., Li, N., Weyns, D., Jin, Z., & Tei, K. (2024) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3686803 · Cited by 77
AI-Augmented SOC: A Survey of LLMs and Agents for Security Automation
Srinivas, S., Kirk, B., Zendejas, J., Espino, M., Boskovich, M., Bari, A., Dajani, K., & Alzahrani, N. (2025) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp5040095 · Cited by 39
LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs
Hadadi, F., Xu, Q., Bianculli, D., & Briand, L. (2024) · arXiv · doi:10.48550/arxiv.2406.07467 · Cited by 7
LINEADAPTER: Parameter-Efficient Fine-Tuning for Log Anomaly Detection and Root Cause Analysis
Liu, X., Bao, W., Zhang, Y., Li, Y., Ranjan, R., & Jha, D. N. (2025) · 2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11322907
Metadata
- Authors
- Ma, Z., Chen, A. R., Kim, D. J., Chen, T.-H., & Wang, S.
- Venue
- Proceedings of the IEEE/ACM 46th International Conference on Software Engineering
- Publisher
- ACM
- Published
- 2024-04-12
- Pages
- 1-13
- OpenAlex
- W4394745212
- Cited by
- 92
- References
- 21
- FWCI
- 41.88
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing. https://app.cochat.ai/papers/10.1145/3597503.3639150
- The paper
- Ma, Z., Chen, A. R., Kim, D. J., Chen, T.-H., & Wang, S. (2024). LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing. Proceedings of the IEEE/ACM 46th International Conference on Software Engineering. https://doi.org/10.1145/3597503.3639150
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.