A Comparative Study on Large Language Models for Log Parsing

• URL: http://arxiv.org/abs/2409.02474v1
• Date: Wed, 4 Sep 2024 06:46:31 GMT
• Title: A Comparative Study on Large Language Models for Log Parsing
• Authors: Merve Astekin, Max Hort, Leon Moonen,
• Abstract summary: We investigate the current capability of state-of-the-art large language models to perform log parsing. We design two different prompting approaches and apply the LLMs on 1, 354 log templates across 16 different projects. We found that free-to-use models are able to compete with paid models, with CodeLlama extracting 10% more log templates correctly than GPT-3.5.
• Score: 3.3590922002216197
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Background: Log messages provide valuable information about the status of software systems. This information is provided in an unstructured fashion and automated approaches are applied to extract relevant parameters. To ease this process, log parsing can be applied, which transforms log messages into structured log templates. Recent advances in language models have led to several studies that apply ChatGPT to the task of log parsing with promising results. However, the performance of other state-of-the-art large language models (LLMs) on the log parsing task remains unclear. Aims: In this study, we investigate the current capability of state-of-the-art LLMs to perform log parsing. Method: We select six recent LLMs, including both paid proprietary (GPT-3.5, Claude 2.1) and four free-to-use open models, and compare their performance on system logs obtained from a selection of mature open-source projects. We design two different prompting approaches and apply the LLMs on 1, 354 log templates across 16 different projects. We evaluate their effectiveness, in the number of correctly identified templates, and the syntactic similarity between the generated templates and the ground truth. Results: We found that free-to-use models are able to compete with paid models, with CodeLlama extracting 10% more log templates correctly than GPT-3.5. Moreover, we provide qualitative insights into the usability of language models (e.g., how easy it is to use their responses). Conclusions: Our results reveal that some of the smaller, free-to-use LLMs can considerably assist log parsing compared to their paid proprietary competitors, especially code-specialized models.

Related papers

• SoK: LLM-based Log Parsing [2.2779174914142346]
  This paper systematically reviews 29 large language models (LLMs)-based log parsing methods. We analyze the learning and prompt-engineering paradigms employed, efficiency- and effectiveness-enhancing techniques, and the role of LLMs in the parsing process.
  arXiv  Detail & Related papers  (2025-04-07T09:41:04Z)
• Idiosyncrasies in Large Language Models [54.26923012617675]
  We unveil and study idiosyncrasies in Large Language Models (LLMs) We find that fine-tuning existing text embedding models on LLM-generated texts yields excellent classification accuracy. We leverage LLM as judges to generate detailed, open-ended descriptions of each model's idiosyncrasies.
  arXiv  Detail & Related papers  (2025-02-17T18:59:02Z)
• Studying and Benchmarking Large Language Models For Log Level Suggestion [49.176736212364496]
  Large Language Models (LLMs) have become a focal point of research across various domains. This paper investigates the impact of characteristics and learning paradigms on the performance of 12 open-source LLMs in log level suggestion.
  arXiv  Detail & Related papers  (2024-10-11T03:52:17Z)
• Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA [51.3033125256716]
  We model the subgraph retrieval task as a conditional generation task handled by small language models. Our base generative subgraph retrieval model, consisting of only 220M parameters, competitive retrieval performance compared to state-of-the-art models. Our largest 3B model, when plugged with an LLM reader, sets new SOTA end-to-end performance on both the WebQSP and CWQ benchmarks.
  arXiv  Detail & Related papers  (2024-10-08T15:22:36Z)
• LibreLog: Accurate and Efficient Unsupervised Log Parsing Using Open-Source Large Language Models [3.7960472831772774]
  This paper introduces LibreLog, an unsupervised log parsing approach that enhances privacy and reduces operational costs while achieving state-of-the-art parsing accuracy. Our evaluation on LogHub-2.0 shows that LibreLog achieves 25% higher parsing accuracy and processes 2.7 times faster compared to state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2024-08-02T21:54:13Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• Stronger, Cheaper and Demonstration-Free Log Parsing with LLMs [18.240096266464544]
  We propose LogBatcher, a cost-effective LLM-based log that requires no training process or labeled data. We have conducted experiments on 16 public log datasets and the results show that LogBatcher is effective for log parsing.
  arXiv  Detail & Related papers  (2024-06-10T10:39:28Z)
• Log Parsing with Self-Generated In-Context Learning and Self-Correction [15.93927602769091]
  Despite a variety of log parsing methods that have been proposed, their performance on evolving log data remains unsatisfactory due to reliance on human-crafted rules or learning-based models with limited training data. We propose Ada, an effective and adaptive log parsing framework using LLMs with self-generated in-context learning (SG-ICL) and self-correction.
  arXiv  Detail & Related papers  (2024-06-05T15:31:43Z)
• Aligning Language Models with Demonstrated Feedback [58.834937450242975]
  Demonstration ITerated Task Optimization (DITTO) directly aligns language model outputs to a user's demonstrated behaviors. We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts.
  arXiv  Detail & Related papers  (2024-06-02T23:13:56Z)
• LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing [8.647406441990396]
  We study the potential of using Large Language Models (LLMs) for log parsing and propose an LLM-based log based on generative inferences and few-shot tuning. 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 time. We also find that using LLMs pre-trained using logs from other systems does not always improve parsing accuracy.
  arXiv  Detail & Related papers  (2024-04-27T20:34:29Z)
• BLESS: Benchmarking Large Language Models on Sentence Simplification [55.461555829492866]
  We present BLESS, a performance benchmark of the most recent state-of-the-art large language models (LLMs) on the task of text simplification (TS) We assess a total of 44 models, differing in size, architecture, pre-training methods, and accessibility, on three test sets from different domains (Wikipedia, news, and medical) under a few-shot setting. Our evaluation indicates that the best LLMs, despite not being trained on TS, perform comparably with state-of-the-art TS baselines.
  arXiv  Detail & Related papers  (2023-10-24T12:18:17Z)
• AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators [98.11286353828525]
  GPT-3.5 series models have demonstrated remarkable few-shot and zero-shot ability across various NLP tasks. We propose AnnoLLM, which adopts a two-step approach, explain-then-annotate. We build the first conversation-based information retrieval dataset employing AnnoLLM.
  arXiv  Detail & Related papers  (2023-03-29T17:03:21Z)
• Self-Supervised Log Parsing [59.04636530383049]
  Large-scale software systems generate massive volumes of semi-structured log records. Existing approaches rely on log-specifics or manual rule extraction. We propose NuLog that utilizes a self-supervised learning model and formulates the parsing task as masked language modeling.
  arXiv  Detail & Related papers  (2020-03-17T19:25:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.