SOTAVerified

Log Parsing

Log Parsing is the task of transforming unstructured log data into a structured format that can be used to train machine learning algorithms. The structured log data is then used to identify patterns, trends, and anomalies, which can support decision-making and improve system performance, security, and reliability. The log parsing process involves the extraction of relevant information from log files, the conversion of this information into a standardized format, and the storage of the structured data in a database or other data repository.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 29 papers

TitleStatusHype
Log Parsing: How Far Can ChatGPT Go?Code1
Log-based Anomaly Detection Without Log ParsingCode1
Lost in Translation? Converting RegExes for Log Parsing into Dynatrace Pattern Language—0
ADALog: Adaptive Unsupervised Anomaly detection in Logs with Self-attention Masked Language Model—0
Deep Learning-based Intrusion Detection Systems: A Survey—0
A Comparative Study on Large Language Models for Log Parsing—0
LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models—0
HELP: Hierarchical Embeddings-based Log Parsing—0
OptLLM: Optimal Assignment of Queries to Large Language ModelsCode0
ECLIPSE: Semantic Entropy-LCS for Cross-Lingual Industrial Log Parsing—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.