mlsanityData to 7 Oct 2026

Debugging Tabular Log as Dynamic Graphs

arXiv 2512.22903 ↗First posted 28 Dec 2025cs.LG cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Tabular log abstracts objects and events in the real-world system and reports their updates to reflect the change of the system, where one can detect real-world inconsistencies efficiently by debugging corresponding log entries. However, recent advances in processing text-enriched tabular log data overly depend on large language models (LLMs) and other heavy-load models, thus suffering from limited flexibility and scalability. This paper proposes a new framework, GraphLogDebugger, to debug tabular log based on dynamic graphs. By constructing heterogeneous nodes for objects and events and connecting node-wise edges, the framework recovers the system behind the tabular log as an evolving dynamic graph. With the help of our dynamic graph modeling, a simple dynamic Graph Neural Network (GNN) is representative enough to outperform LLMs in debugging tabular log, which is validated by experimental results on real-world log datasets of computer systems and academic papers.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 84 references that are in the map. First posted on arXiv 28 Dec 2025.

Builds on

52 of 84 references.

References · 52

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2017Graph Attention Networkscited by 8,854
  7. 2017Inductive Representation Learning on Large Graphscited by 6,284
  8. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  9. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  10. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
  11. 2020Benchmarking Graph Neural Networkscited by 672
  12. 2020Knowledge Graphscited by 619
38 more
  1. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  2. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 521
  3. 2020Inductive Representation Learning on Temporal Graphscited by 454
  4. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  5. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
  6. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
  7. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  8. 2024Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understandingcited by 185
  9. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  10. 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systemscited by 170
  11. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  12. 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 137
  13. 2022ROLAND: Graph Learning Framework for Dynamic Graphscited by 131
  14. 2021LogBERT: Log Anomaly Detection via BERTcited by 114
  15. 2023The Semantic Scholar Open Data Platformcited by 109
  16. 2019On the Use of ArXiv as a Datasetcited by 101
  17. 2024From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflectioncited by 93
  18. 2023Temporal Data Meets LLM -- Explainable Financial Time Series Forecastingcited by 77
  19. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  20. 2024Large Scale Transfer Learning for Tabular Data via Language Modelingcited by 73
  21. 2020Loghub: A Large Collection of System Log Datasets for AI-driven Log Analyticscited by 68
  22. 2023Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunitiescited by 60
  23. 2023Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoningcited by 44
  24. 2024MIRAI: Evaluating LLM Agents for Event Forecastingcited by 40
  25. 2023Rethinking Tabular Data Understanding with Large Language Modelscited by 34
  26. 2023LogGPT: Exploring ChatGPT for Log-Based Anomaly Detectioncited by 33
  27. 2021LAnoBERT: System Log Anomaly Detection based on BERT Masked Language Modelcited by 30
  28. 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discoverycited by 27
  29. 2024DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphscited by 26
  30. 2024LogParser-LLM: Advancing Efficient Log Parsing with Large Language Modelscited by 20
  31. 2023RAGLog: Log Anomaly Detection using Retrieval Augmented Generationcited by 19
  32. 2022AntiBenford Subgraphs: Unsupervised Anomaly Detection in Financial Networkscited by 18
  33. 2024Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftscited by 18
  34. 2024Anomaly Detection in Dynamic Graphs: A Comprehensive Surveycited by 18
  35. 2025LLM-based event log analysis techniques: A surveycited by 15
  36. 2025Graph World Modelcited by 14
  37. 2025Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challengescited by 10
  38. 2024Text2TimeSeries: Enhancing Financial Forecasting through Time Series Prediction Updates with Event-Driven Insights from Large Language Modelscited by 9

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.