Unleashing the True Potential of Semantic-Based Log Parsing with Pre-Trained Language Models

Software-intensive systems often produce console logs for troubleshooting purposes. Log parsing, which aims at parsing a log message into a specific log template, typically serves as the first step toward automated log analytics. To better comprehend the semantic information of log messages, many se...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / International Conference on Software Engineering pp. 975 - 987
Main Authors: Le, Van-Hoang, Xiao, Yi, Zhang, Hongyu
Format: Conference Proceeding
Language:English
Published: IEEE 26.04.2025
Subjects:
ISSN:1558-1225
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Software-intensive systems often produce console logs for troubleshooting purposes. Log parsing, which aims at parsing a log message into a specific log template, typically serves as the first step toward automated log analytics. To better comprehend the semantic information of log messages, many semantic-based log parsers have been proposed. These log parsers fine-tune a small pre-trained language model (PLM) such as RoBERTa on a few labelled log samples. With the increasing popularity of large language models (LLMs), some recent studies also propose to leverage LLMs such as ChatGPT through in-context learning for automated log parsing and obtain better results than previous semantic-based log parsers with small PLMs. In this paper, we show that semantic-based log parsers with small PLMs can actually achieve better or comparable performance to state-of-the-art LLM-based log parsing models while being more efficient and cost-effective. We propose Unleash, a novel semantic-based log parsing approach, which incorporates three enhancement methods to boost the performance of PLMs for log parsing, including (1) an entropy-based ranking method to select the most informative log samples; (2) a contrastive learning method to enhance the fine-tuning process; and (3) an inference optimization method to improve the log parsing performance. We evaluate Unleash on a set of large-scale, public log datasets and the experimental results show that Unleash is effective and efficient compared to state-of-the-art log parsers.
AbstractList Software-intensive systems often produce console logs for troubleshooting purposes. Log parsing, which aims at parsing a log message into a specific log template, typically serves as the first step toward automated log analytics. To better comprehend the semantic information of log messages, many semantic-based log parsers have been proposed. These log parsers fine-tune a small pre-trained language model (PLM) such as RoBERTa on a few labelled log samples. With the increasing popularity of large language models (LLMs), some recent studies also propose to leverage LLMs such as ChatGPT through in-context learning for automated log parsing and obtain better results than previous semantic-based log parsers with small PLMs. In this paper, we show that semantic-based log parsers with small PLMs can actually achieve better or comparable performance to state-of-the-art LLM-based log parsing models while being more efficient and cost-effective. We propose Unleash, a novel semantic-based log parsing approach, which incorporates three enhancement methods to boost the performance of PLMs for log parsing, including (1) an entropy-based ranking method to select the most informative log samples; (2) a contrastive learning method to enhance the fine-tuning process; and (3) an inference optimization method to improve the log parsing performance. We evaluate Unleash on a set of large-scale, public log datasets and the experimental results show that Unleash is effective and efficient compared to state-of-the-art log parsers.
Author Le, Van-Hoang
Zhang, Hongyu
Xiao, Yi
Author_xml – sequence: 1
  givenname: Van-Hoang
  surname: Le
  fullname: Le, Van-Hoang
  email: hoang.le@newcastle.edu.au
  organization: The University of Newcastle,Australia
– sequence: 2
  givenname: Yi
  surname: Xiao
  fullname: Xiao, Yi
  email: yixiao@cqu.edu.cn
  organization: Chongqing University,China
– sequence: 3
  givenname: Hongyu
  surname: Zhang
  fullname: Zhang, Hongyu
  email: hyzhang@cqu.edu.cn
  organization: Chongqing University,China
BookMark eNotkMFKw0AURUdRsK39gy7mB1Lfm8kkmaWWqoWIgaY7obw0r-lIOpFMivj3tujqcjncs7hjceM7z0LMEOaIYB9Wi_XSGB2ncwXKzAEwja_E1KY20xoNmMTitRihMVmESpk7MQ7hEwCS2NqR-Nj4likcnG_kcGBZ9ieWRTewHxy1stvLNR_pXHbREwWuZd41sqA-XAbfbjjIoueo7Mn5CyTfnKhh-dbV3IZ7cbunNvD0Pydi87wsF69R_v6yWjzmEakEhmiXMtaqImNxp1VVMdQU6yrJ1J4pQSKCjDOycW0TA1wz6VQrRqqsJjSxnojZn9cx8_ard0fqf7bne5TNlNW_sjdWSA
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICSE55347.2025.00174
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
Business
EISBN 9798331505691
EISSN 1558-1225
EndPage 987
ExternalDocumentID 11029829
Genre orig-research
GroupedDBID -~X
.4S
.DC
29O
5VS
6IE
6IF
6IH
6IK
6IL
6IM
6IN
8US
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
ARCSS
AVWKF
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
EDO
FEDTE
I-F
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-a260t-c7e1d2ba591c32bbe0da43b682fea61aaa08e8a94d9650edea3732e1ab93a1543
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001538318100076&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 01:40:09 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a260t-c7e1d2ba591c32bbe0da43b682fea61aaa08e8a94d9650edea3732e1ab93a1543
PageCount 13
ParticipantIDs ieee_primary_11029829
PublicationCentury 2000
PublicationDate 2025-April-26
PublicationDateYYYYMMDD 2025-04-26
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-April-26
  day: 26
PublicationDecade 2020
PublicationTitle Proceedings / International Conference on Software Engineering
PublicationTitleAbbrev ICSE
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0006499
Score 2.3101478
Snippet Software-intensive systems often produce console logs for troubleshooting purposes. Log parsing, which aims at parsing a log message into a specific log...
SourceID ieee
SourceType Publisher
StartPage 975
SubjectTerms Business
Chatbots
Contrastive learning
Large language models
log analytics
log parsing
Optimization methods
pre-trained LMs
Scalability
Semantics
Software engineering
Title Unleashing the True Potential of Semantic-Based Log Parsing with Pre-Trained Language Models
URI https://ieeexplore.ieee.org/document/11029829
WOSCitedRecordID wos001538318100076&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NawIxEA1VSunJ1lr6TQ69pm6y2WRzrSgtiAgqeChIPmaLYHeLrv39TdbV9tJDb2EDG5hhdl5m5u1D6DEyjkKmHLGZ5YRzCUQ5R0NcgUm0D02oPD2Uo1E6n6txTVavuDAAUA2fwVNYVr18V9htKJV1fapiKmWqgRpSih1Z6_DZFR6719w4Gqnua2_ST5KYS38HZKFuQsNM3y8FlSqBDFr_PPoMdX6oeHh8SDLn6AjyNjrZj6u3UWsvy4DrKL1Ab7N8BTuNJOzhHZ6ut_4dRRnmgvQKFxmewIc36NKSZ5_DHB4W73isq6oBDnVZfyCQadCOCJt1QRMH1bTVpoNmg_6090JqEQWi_VWlJFYCdczoRFEbM2MgcprHRqQsAy2o1jpKIdWKO-XBGjjQsYwZUG1UrD2-ii9RMy9yuEJYSGFcJowJ3XqRJUZT6yEAZKlhTnF-jTrBcIvP3X8yFnub3fzx_BadBt-E3gwTd6hZenPco2P7VS4364fKu98lK6eA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4UjXpCEeNve_BaWbuuW68SCMRJSICEgwlp1zdDgpuB4d9vOwZ68eCtWZM1eS9v7-t779uH0KOnDYVUGpKkCSech0CkMdTFFehA2dCE0tNxOBhE06kcVmT1kgsDAOXwGTy5ZdnLN3mydqWylk1VTEZM7qODgHPmbehauw-vsOi9YsdRT7b67VEnCHwe2lsgc5UT6qb6fmmolCmkW__n4aeo-UPGw8NdmjlDe5A10NF2YL2B6lthBlzF6Tl6m2QL2KgkYQvw8Hi5tu_ICzcZpBY4T_EIPqxJ5wl5tlnM4Dh_x0NV1g2wq8zaA4GMnXqE26xKmtjppi1WTTTpdsbtHqlkFIiyl5WCJCFQw7QKJE18pjV4RnFfi4iloARVSnkRREpyIy1cAwPKD30GVGnpK4uw_AtUy_IMLhEWodAmFVq7fr1IA61oYkEApJFmRnJ-hZrOcLPPzZ8yZlubXf_x_AEd98av8SzuD15u0Inzk-vUMHGLaoU1zR06TL6K-Wp5X3r6GwjKqsc
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%2F+International+Conference+on+Software+Engineering&rft.atitle=Unleashing+the+True+Potential+of+Semantic-Based+Log+Parsing+with+Pre-Trained+Language+Models&rft.au=Le%2C+Van-Hoang&rft.au=Xiao%2C+Yi&rft.au=Zhang%2C+Hongyu&rft.date=2025-04-26&rft.pub=IEEE&rft.eissn=1558-1225&rft.spage=975&rft.epage=987&rft_id=info:doi/10.1109%2FICSE55347.2025.00174&rft.externalDocID=11029829