Debugging Tabular Log as Dynamic Graphs
This work addresses the limited flexibility and scalability of LLM-based methods for debugging tabular logs in systems like computer systems and academic papers, offering a more efficient alternative.
The paper tackles the problem of debugging tabular log data by proposing GraphLogDebugger, a framework that models logs as dynamic graphs, and shows that a simple dynamic GNN outperforms LLMs in this task, as validated on real-world datasets.
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.