ThinkLog: Leveraging Reasoning for Log Statement Generation

• URL: http://arxiv.org/abs/2607.11615v1
• Date: Mon, 13 Jul 2026 14:37:35 GMT
• Title: ThinkLog: Leveraging Reasoning for Log Statement Generation
• Abstract summary: ThinkLog is an end-to-end log statement generation method.<n>It incorporates reasoning that helps LLMs make decisions about log insertion, severity level assignment, and message generation.<n>It achieves 20.55% log statement generation accuracy, representing a 15.4% improvement over the best existing method.
• Score: 4.372207458643732
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Runtime logs are an important source of information that supports software maintenance. To obtain useful logs, developers spend significant effort identifying appropriate log locations, assigning correct severity levels, and writing concise yet informative messages. Therefore, end-to-end automated log statement generation can help reduce this burden, and prior work has proposed many methods for this task. However, existing methods still exhibit limited accuracy. To address this problem, we propose ThinkLog, an LLM-based end-to-end log statement generation method. The core idea of ThinkLog is to incorporate reasoning that helps LLMs make decisions about log insertion, severity level assignment, and message generation, thereby improving log statement generation accuracy. ThinkLog injects reasoning into prompts as few-shot examples and guides LLMs to generate appropriate log statements. Evaluated on 9,619 Java methods extracted from public GitHub repositories, ThinkLog achieves 20.55% log statement generation accuracy, representing a 15.4% improvement over the best existing method. Moreover, these improvements were achieved at approximately 50% of the inference cost (USD) compared to the best existing method. These results show that leveraging reasoning is an effective and cost-efficient way to improve the accuracy of end-to-end log statement generation.

Related papers

• OrLog: Resolving Complex Queries with LLMs and Probabilistic Reasoning [51.58235452818926]
  We introduce OrLog, a neuro-symbolic retrieval framework that decouples predicate-level plausibility estimation from logical reasoning.<n>A large language model (LLM) provides plausibility scores for atomic predicates in one decoding-free forward pass, from which a probabilistic reasoning engine derives the posterior probability of query satisfaction.
  arXiv  Detail & Related papers  (2026-01-30T15:31:58Z)
• PDLogger: Automated Logging Framework for Practical Software Development [7.860311994179783]
  Existing automated logging techniques focus on isolated sub-tasks.<n>PDLogger is the first end-to-end log generation technique expressly designed for practical, multi-log scenarios.<n>It improves log-position precision by 139.0 percent, F1 by 69.2 percent, level accuracy by 82.3 percent, variable precision by 131.8 percent, and message quality (BERTScore) by 65.7 percent.
  arXiv  Detail & Related papers  (2025-07-26T13:35:57Z)
• 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)
• Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework [50.02710905062184]
  This paper proposes an automated design-data augmentation framework, which generates high-volume and high-quality natural language aligned with Verilog and EDA scripts. The accuracy of Verilog generation surpasses that of the current state-of-the-art open-source Verilog generation model, increasing from 58.8% to 70.6% with the same benchmark.
  arXiv  Detail & Related papers  (2024-03-17T13:01:03Z)
• Log Statements Generation via Deep Learning: Widening the Support Provided to Developers [16.079459379684554]
  LANCE is an approach rooted in deep learning (DL) that has demonstrated the ability to correctly inject a log statement into Java methods. We present LEONID, a DL-based technique that can distinguish between methods that do and do not require the inclusion of log statements.
  arXiv  Detail & Related papers  (2023-11-08T10:31:18Z)
• FastLog: An End-to-End Method to Efficiently Generate and Insert Logging Statements [5.80502312468937]
  We propose FastLog, which can support the complete logging statement generation and insertion activity. FastLog first predicts the insertion position in the finest token level, and then generates a complete logging statement to insert. A comprehensive empirical analysis shows that our method outperforms the state-of-the-art approach in both efficiency and output quality.
  arXiv  Detail & Related papers  (2023-11-06T04:26:20Z)
• A Large-Scale Evaluation for Log Parsing Techniques: How Far Are We? [42.56249610409624]
  We provide a new collection of annotated log datasets, denoted Loghub-2.0, which can better reflect the characteristics of log data in real-world software systems. We conduct a thorough re-evaluation of 15 state-of-the-art logs in a more rigorous and practical setting. Particularly, we introduce a new evaluation metric to mitigate the sensitivity of existing metrics to imbalanced data distributions.
  arXiv  Detail & Related papers  (2023-08-21T16:24:15Z)
• Prompting for Automatic Log Template Extraction [6.299547112893045]
  DivLog is an effective log parsing framework based on the incontext learning (ICL) ability of large language models (LLMs) By mining the semantics of examples in the prompt, DivLog generates a target log template in a training-free manner.
  arXiv  Detail & Related papers  (2023-07-19T12:44:59Z)
• Data-Driven Approach for Log Instruction Quality Assessment [59.04636530383049]
  There are no widely adopted guidelines on how to write log instructions with good quality properties. We identify two quality properties: 1) correct log level assignment assessing the correctness of the log level, and 2) sufficient linguistic structure assessing the minimal richness of the static text necessary for verbose event description. Our approach correctly assesses log level assignments with an accuracy of 0.88, and the sufficient linguistic structure with an F1 score of 0.99, outperforming the baselines.
  arXiv  Detail & Related papers  (2022-04-06T07:02:23Z)
• Borrowing from Similar Code: A Deep Learning NLP-Based Approach for Log Statement Automation [0.0]
  We introduce an updated and improved log-aware code-clone detection method to predict the location of logging statements. We incorporate natural language processing (NLP) and deep learning methods to automate the log statements' description prediction. Our analysis shows that our hybrid NLP and code-clone detection approach (NLP CC'd) outperforms conventional clone detectors in finding log statement locations.
  arXiv  Detail & Related papers  (2021-12-02T14:03:49Z)
• Leveraging Code Clones and Natural Language Processing for Log Statement Prediction [0.0]
  This research aims to predict the log statements by utilizing source code clones and natural language processing (NLP) Our work demonstrates the effectiveness of log-aware clone detection for automated log location and description prediction.
  arXiv  Detail & Related papers  (2021-09-08T18:17:45Z)
• 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.