BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/London
X-WR-TIMEZONE:Europe/London
BEGIN:VEVENT
UID:99@oxon.bcs.org
DTSTART;TZID=Europe/London:20260513T193000
DTEND;TZID=Europe/London:20260513T210000
DTSTAMP:20260413T130441Z
URL:https://oxon.bcs.org/programme/code-smells-human-written-vs-llm-genera
 ted-programs/
SUMMARY:Code Smells: Human-Written vs LLM Generated Programs
DESCRIPTION:\nHong Zhu\, School of Engineering\, Computing and Mathematics\
 , Oxford Brookes University\nCode smells are indications of quality issues
  that are present in program code in the form of certain syntactic structu
 res and patterns of code metrics. Although they are not bugs that cause so
 ftware fail\, they result in difficulty and cost in software maintenance\,
  evolution\, and reuse. Since Beck and Fowler introduced the term “code 
 smells” in 2018\, intensive research has been reported in the literature
  on understanding the impact of code smells on various software quality at
 tributes in the revision and transition categories\, developing techniques
  and tools for detecting code smells and refactoring program code to reduc
 e code smells.  It is now widely applied in software engineering practice
 .\n\nIn recent years\, with the rapid advance of machine learning (ML) in 
 natural and programming language processing\, large language models (LLMs)
  have become increasingly used in software development practice. LLM’s p
 erformance in code generation is a key element of the leader boards of LLM
  competition. However\, existing works have mostly focused on the function
 al correctness of generated code\, while research found that the major dri
 ving force for the adoption of generated code is not its correctness but w
 hether it is useful as a starting point for further development. A questio
 n is how to evaluate the usefulness of generated code for further developm
 ent. In this talk\, we argue that code smell detection and assessment coul
 d offer a good answer to this question.\n\nThe talk will consist of two pa
 rts. The first introduce the notion of code smells\, and briefly reviews t
 he techniques and automated tools for detecting code smells. The second re
 ports our experiments with on detecting the smells of LLM generated code a
 nd comparing them with code written by professional programmers.\nAbout Ho
 ng Zhu\nDr. Hong Zhu is a Professor of Computer Science at the Oxford Broo
 kes University\, Oxford\, UK\, where he was the Chair of Applied Formal Me
 thods Research Group and now chairs the Cloud Computing And Cybersecurity 
 Research Group. He obtained his BSc\, MSc and PhD degrees in Computer Scie
 nce from Nanjing University\, China\, in 1982\, 1984 and 1987\, respective
 ly. He was a faculty member of Nanjing University from 1987 to 1998 as a L
 ecturer\, Associate Professor and Full Professor and PhD Student Superviso
 r. He joined Oxford Brookes University in November 1998. His research inte
 rests are in software development methodologies\, including software engin
 eering of cloud-native applications\, software engineering of AI and machi
 ne learning applications\, multi-agent systems\, formal methods\, software
  design\, software testing\, programming languages\, software modelling\, 
 and automated software engineering tools and environments\, etc. He has pu
 blished 2 books and more than 200 research papers in journals and internat
 ional conferences. He is a senior member of IEEE\, a member of British Com
 puter Society\, and ACM. He is a co-founder of the IEEE/ACM International 
 Workshop/ Conference series on Automation of Software Test (AST) and a co-
 founder of the IEEE International Conference series on Artificial Intellig
 ence Test (AITest). He is a member of the Editorial Board of the Software 
 Quality Journal and a member of the Steering Committee of the IEEE Interna
 tional Congress on Intelligent Service Oriented Systems Engineering (IEEE 
 CISOSE). He has also served numerous international conferences as a Genera
 l Chair\, PC chair and PC members and a reviewer for numerous journals and
  research funding bodies.
ATTACH;FMTTYPE=image/jpeg:https://oxon.bcs.org/wp-content/uploads/2025/09/
 AI-Code-Reviewer-Thumb.png
CATEGORIES:Hybrid Event
LOCATION:Rewley House\, 1 Wellington Square\, Oxford\, Oxfordshire\, OX1 2J
 A\, United Kingdom
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=1 Wellington Square\, Oxfor
 d\, Oxfordshire\, OX1 2JA\, United Kingdom;X-APPLE-RADIUS=100;X-TITLE=Rewl
 ey House:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/London
X-LIC-LOCATION:Europe/London
BEGIN:DAYLIGHT
DTSTART:20260329T020000
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR