SlideShare a Scribd company logo
1 of 28
Download to read offline
1
2
Variants of code (e.g., Java or C)
Variants of user interfaces
Variants of video sequences
Variants of models (e.g., UML or
SysML)
Variants of « things » (3D
models)
…
Variability Models (feature models)
Reverse engineering
variability and
reusable assets e4CompareFramework
ECCO tool
3
Problem: Given a set of variants, how to synthesize a
program that can be configured to retrieve original variants?
?????????
4
Problem: Given a set of variants, how to synthesize a
program that can be configured to retrieve original variants?
SPL = feature model + annotated program (eg template-based generator)
Expected properties: soundness/completeness/meaningful set of features
(for configuration or maintenance/evolution/expansion)
Reverse engineering
variability and
reusable assets Error-prone
Time-consuming
e4CompareFramework
ECCO tool
5
Problem: Given a set of variants, how to synthesize a
program that can be configured to retrieve original variants?
SPL = feature model + annotated program (eg template-based generator)
Expected properties: soundness/completeness/meaningful set of features
(for configuration or maintenance/evolution/expansion)
Hypothesis: large language models (LLMs)
can assist domain experts and developers in
some re-engineering activities Error-prone
Time-consuming
6
Research method
LLM = ChatGPT4 (no API)
Session: sequence of prompts until getting a result
Within a session, we, as users, asked for different tasks such as:
● domain analysis, summary of commonalities and differences, as plain languages or as tables,
● identification of features,
● synthesis of an integrated, 150% model or code (and possibly a
● visualization)
● synthesis of a template-based generator
● refactoring of models or code, corrections of code, model, or explanations that were perceived as inaccurate or simply
unusable.
Highly-interactive
Repetition of some sessions (with some prompts’ variations)
Qualitative assessment 7
Research method: 5 cases with ChatGPT4
We consider five cases:
● Java variants
● UML variants
● state chart variants
● state machine variants
● PNG image variants
We revisit some of the cases considered by
https://github.com/but4reuse/but4reuse/wiki/Examples, this time with generative AI
Qualitative assessment
e4CompareFramework
ECCO tool
8
Case #1: BANKING SYSTEMS VARIANTS IN JAVA
9
10
11
12
13
Case #2: BANKING SYSTEMS VARIANTS IN UML
14
Case #2: BANKING SYSTEMS VARIANTS IN UML
15
Case #3: GRAPHML
VARIANTS
16
Case #3: GRAPHML
VARIANTS
17
Case #4: STATECHARTS VARIANTS
18
Case #5: PGN VARIANTS
With current LLMs, we confirm (1) the impossibility to analyze PNG,
binary files and compute a relevant diff – there are no magical
solutions involved;
(2) the provision of pixels location to LLM does not scale: there is
simply too much information to fed in; (3) LLM is not helpful to
find meaningful features: the information is too low-level and there
is no semantic to infer.
19
Discussion
Limitations:
● size of input variants
○ Limited context-window and long-term memory
○ Impossible to fed a large XML file or an entire project (eg ArgoUML case)
● inaccuracies
○ See eg Case 2
● similarity function can work “out of the box” (language agnostic)
● …but we know that similarity function is usually highly specific to a
programming/modelling languages
Threats: prompts used, LLM (= ChatGPT4)
Challenge: a re-engineering benchmark for generative AI/LLM
20
Problem: Given a set of variants, how to synthesize a
program that can be configured to retrieve original variants?
Positive and negative experiences
Potential: automation of template synthesis, feature identification/naming, refactoring, etc.
Strong limitations: prompt sensitivity, size of the input, inaccuracies
Instead of thinking of ChatGPT as a replacement of BUT4Reuse or similar frameworks,
the integration of both could be a more beneficial solution for the moment.
Error-prone
Time-consuming
Hypothesis: large language models (LLMs)
can assist domain experts and developers in
some re-engineering activities
21
https://github.com/acherm/variantsGPT
Paper available: https://inria.hal.science/hal-04160693/
22
I’d like to change the color of the cat’s tail
On
programming
variability
with LLMs
Here is a TikZ code:
tikzset{%
cat/.pic={
tikzset{x=3cm/5,y=3cm/5,shift={(0,-1/3)}}
useasboundingbox (-1,-1) (1,2);
fill [BlueGrey900] (0,-2)
.. controls ++(180:3) and ++(0:5/4) .. (-2,0)
arc (270:90:1/5)
.. controls ++(0:2) and ++(180:11/4) .. (0,-2+2/5);
foreach i in {-1,1}
scoped[shift={(1/2*i,9/4)}, rotate=45*i]{
clip [overlay] (0, 5/9) ellipse [radius=8/9];
clip [overlay] (0,-5/9) ellipse [radius=8/9];
fill [BlueGrey900] ellipse [radius=1];
clip [overlay] (0, 7/9) ellipse [radius=10/11];
clip [overlay] (0,-7/9) ellipse [radius=10/11];
fill [Purple100] ellipse [radius=1];
};
fill [BlueGrey900] ellipse [x radius=3/4, y radius=2];
fill [BlueGrey100] ellipse [x radius=1/3, y radius=1];
fill [BlueGrey900]
(0,15/8) ellipse [x radius=1, y radius=5/6]
(0, 8/6) ellipse [x radius=1/2, y radius=1/2]
{[shift={(-1/2,-2)}, rotate= 10] ellipse [x radius=1/3, y
radius=5/4]}
{[shift={( 1/2,-2)}, rotate=-10] ellipse [x radius=1/3, y
radius=5/4]};
fill [BlueGrey500]
(-1/9,11/8) ellipse [x radius=1/5, y radius=1/5]
( 1/9,11/8) ellipse [x radius=1/5, y radius=1/5];
fill [Purple100]
(0,12/8) ellipse [x radius=1/10, y radius=1/5]
(0,12/8+1/9) ellipse [x radius=1/5 , y radius=1/10];
foreach i in {-1,1}
scoped[shift={(1/2*i,2)}, rotate=35*i]{
clip [overlay] (0, 1/7) ellipse [radius=2/7];
clip [overlay] (0,-1/7) ellipse [radius=2/7];
fill [Yellow50] ellipse [radius=1];
};
scoped{
clip (-1,-2) rectangle ++(2,1);
fill [BlueGrey900] (0,-2) ellipse [radius=1/2];
fill [Grey100]
(-1/2,-2) ellipse [x radius=1/3, y radius=1/4]
( 1/2,-2) ellipse [x radius=1/3, y radius=1/4];
};
foreach i in {-1,1}
23
Backup slides
24
https://github.com/acherm/variantsGPT
25
Code synthesis
with LLMs
vs Codex
https://arxiv.org/abs/2210.14699
26
Generative programming [Czarnecki2000], Model-driven engineering:
automatically generate variants from a specification written in one or more textual or
graphical domain-specific languages
Accidental and
essential complexity
Variability further
increases this
software
complexity: multiple
features, code
variations, and an
exponential number
of possible variants
27
LLM
Hypothesis: Large language models (LLMs) act as a new variability compiler capable of
transforming a high-level specification (“prompt”) into variable code, features, generators,
configurable systems, etc. written in a given technological space.
Motto: “features as prompts” 28

More Related Content

What's hot

C#のキモイ高速プログラミング
C#のキモイ高速プログラミングC#のキモイ高速プログラミング
C#のキモイ高速プログラミングKaisei Sunaga
 
Azure Machine Learning 重頭學
Azure Machine Learning 重頭學Azure Machine Learning 重頭學
Azure Machine Learning 重頭學Ko Ko
 
MOE, MOP, TPM and the IMP/IMS
MOE, MOP, TPM and the IMP/IMSMOE, MOP, TPM and the IMP/IMS
MOE, MOP, TPM and the IMP/IMSGlen Alleman
 
Agile methodologiesvswaterfall
Agile methodologiesvswaterfallAgile methodologiesvswaterfall
Agile methodologiesvswaterfallMuthu Natarajan
 
PRINCE2 + AGILE = SUCCESS
PRINCE2 + AGILE = SUCCESSPRINCE2 + AGILE = SUCCESS
PRINCE2 + AGILE = SUCCESSJens Hoffmann
 
How to Implement Agile & Scrum in your Startup
How to Implement Agile & Scrum in your StartupHow to Implement Agile & Scrum in your Startup
How to Implement Agile & Scrum in your StartupSycabe
 
OpenCVをAndroidで動かしてみた
OpenCVをAndroidで動かしてみたOpenCVをAndroidで動かしてみた
OpenCVをAndroidで動かしてみた徹 上野山
 
Getting Started GraalVM / GraalVM超入門 #jjug_ccc #ccc_c2
Getting Started GraalVM / GraalVM超入門 #jjug_ccc #ccc_c2Getting Started GraalVM / GraalVM超入門 #jjug_ccc #ccc_c2
Getting Started GraalVM / GraalVM超入門 #jjug_ccc #ccc_c2tamtam180
 
【15-A-4】Redmine + Lychee 導入のアンチパターン
【15-A-4】Redmine + Lychee 導入のアンチパターン【15-A-4】Redmine + Lychee 導入のアンチパターン
【15-A-4】Redmine + Lychee 導入のアンチパターンDevelopers Summit
 
Migration Guide from Java 8 to Java 11 #jjug
Migration Guide from Java 8 to Java 11 #jjugMigration Guide from Java 8 to Java 11 #jjug
Migration Guide from Java 8 to Java 11 #jjugYuji Kubota
 
オンプレでPrivate Registry使ったDockerイメージの運用について
オンプレでPrivate Registry使ったDockerイメージの運用についてオンプレでPrivate Registry使ったDockerイメージの運用について
オンプレでPrivate Registry使ったDockerイメージの運用についてYASUKAZU NAGATOMI
 
Klocwork カスタムチェッカー紹介
Klocwork カスタムチェッカー紹介Klocwork カスタムチェッカー紹介
Klocwork カスタムチェッカー紹介Masaru Horioka
 
How Can Software Engineering Support AI
How Can Software Engineering Support AIHow Can Software Engineering Support AI
How Can Software Engineering Support AIWalid Maalej
 
Java仮想マシンの実装技術
Java仮想マシンの実装技術Java仮想マシンの実装技術
Java仮想マシンの実装技術Kiyokuni Kawachiya
 
MicroProfileの正しい使い方 (Java Developer Summit 2023)
MicroProfileの正しい使い方 (Java Developer Summit 2023)MicroProfileの正しい使い方 (Java Developer Summit 2023)
MicroProfileの正しい使い方 (Java Developer Summit 2023)Hirofumi Iwasaki
 
RSG Taipei 2023 LeSS Design Principles
RSG Taipei 2023 LeSS Design PrinciplesRSG Taipei 2023 LeSS Design Principles
RSG Taipei 2023 LeSS Design PrinciplesJen-Chieh Ko
 

What's hot (20)

C#のキモイ高速プログラミング
C#のキモイ高速プログラミングC#のキモイ高速プログラミング
C#のキモイ高速プログラミング
 
Diagrammi Use Case
Diagrammi Use CaseDiagrammi Use Case
Diagrammi Use Case
 
Azure Machine Learning 重頭學
Azure Machine Learning 重頭學Azure Machine Learning 重頭學
Azure Machine Learning 重頭學
 
MOE, MOP, TPM and the IMP/IMS
MOE, MOP, TPM and the IMP/IMSMOE, MOP, TPM and the IMP/IMS
MOE, MOP, TPM and the IMP/IMS
 
Agile methodologiesvswaterfall
Agile methodologiesvswaterfallAgile methodologiesvswaterfall
Agile methodologiesvswaterfall
 
PRINCE2 + AGILE = SUCCESS
PRINCE2 + AGILE = SUCCESSPRINCE2 + AGILE = SUCCESS
PRINCE2 + AGILE = SUCCESS
 
How to Implement Agile & Scrum in your Startup
How to Implement Agile & Scrum in your StartupHow to Implement Agile & Scrum in your Startup
How to Implement Agile & Scrum in your Startup
 
OpenCVをAndroidで動かしてみた
OpenCVをAndroidで動かしてみたOpenCVをAndroidで動かしてみた
OpenCVをAndroidで動かしてみた
 
Getting Started GraalVM / GraalVM超入門 #jjug_ccc #ccc_c2
Getting Started GraalVM / GraalVM超入門 #jjug_ccc #ccc_c2Getting Started GraalVM / GraalVM超入門 #jjug_ccc #ccc_c2
Getting Started GraalVM / GraalVM超入門 #jjug_ccc #ccc_c2
 
Certified ScrumMaster Training
Certified ScrumMaster TrainingCertified ScrumMaster Training
Certified ScrumMaster Training
 
Agile
AgileAgile
Agile
 
【15-A-4】Redmine + Lychee 導入のアンチパターン
【15-A-4】Redmine + Lychee 導入のアンチパターン【15-A-4】Redmine + Lychee 導入のアンチパターン
【15-A-4】Redmine + Lychee 導入のアンチパターン
 
on log messages
on log messageson log messages
on log messages
 
Migration Guide from Java 8 to Java 11 #jjug
Migration Guide from Java 8 to Java 11 #jjugMigration Guide from Java 8 to Java 11 #jjug
Migration Guide from Java 8 to Java 11 #jjug
 
オンプレでPrivate Registry使ったDockerイメージの運用について
オンプレでPrivate Registry使ったDockerイメージの運用についてオンプレでPrivate Registry使ったDockerイメージの運用について
オンプレでPrivate Registry使ったDockerイメージの運用について
 
Klocwork カスタムチェッカー紹介
Klocwork カスタムチェッカー紹介Klocwork カスタムチェッカー紹介
Klocwork カスタムチェッカー紹介
 
How Can Software Engineering Support AI
How Can Software Engineering Support AIHow Can Software Engineering Support AI
How Can Software Engineering Support AI
 
Java仮想マシンの実装技術
Java仮想マシンの実装技術Java仮想マシンの実装技術
Java仮想マシンの実装技術
 
MicroProfileの正しい使い方 (Java Developer Summit 2023)
MicroProfileの正しい使い方 (Java Developer Summit 2023)MicroProfileの正しい使い方 (Java Developer Summit 2023)
MicroProfileの正しい使い方 (Java Developer Summit 2023)
 
RSG Taipei 2023 LeSS Design Principles
RSG Taipei 2023 LeSS Design PrinciplesRSG Taipei 2023 LeSS Design Principles
RSG Taipei 2023 LeSS Design Principles
 

Similar to Generative AI for Reengineering Variants into Software Product Lines: An Experience Report

Directive-based approach to Heterogeneous Computing
Directive-based approach to Heterogeneous ComputingDirective-based approach to Heterogeneous Computing
Directive-based approach to Heterogeneous ComputingRuymán Reyes
 
EclipseCon Eu 2015 - Breathe life into your Designer!
EclipseCon Eu 2015 - Breathe life into your Designer!EclipseCon Eu 2015 - Breathe life into your Designer!
EclipseCon Eu 2015 - Breathe life into your Designer!melbats
 
SiriusCon 2015 - Breathe Life into Your Designer!
SiriusCon 2015 - Breathe Life into Your Designer!SiriusCon 2015 - Breathe Life into Your Designer!
SiriusCon 2015 - Breathe Life into Your Designer!melbats
 
Fast Insights to Optimized Vectorization and Memory Using Cache-aware Rooflin...
Fast Insights to Optimized Vectorization and Memory Using Cache-aware Rooflin...Fast Insights to Optimized Vectorization and Memory Using Cache-aware Rooflin...
Fast Insights to Optimized Vectorization and Memory Using Cache-aware Rooflin...Intel® Software
 
PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems
PRETZEL: Opening the Black Box of Machine Learning Prediction Serving SystemsPRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems
PRETZEL: Opening the Black Box of Machine Learning Prediction Serving SystemsNECST Lab @ Politecnico di Milano
 
Advanced Graphics Workshop - GFX2011
Advanced Graphics Workshop - GFX2011Advanced Graphics Workshop - GFX2011
Advanced Graphics Workshop - GFX2011Prabindh Sundareson
 
Pretzel: optimized Machine Learning framework for low-latency and high throug...
Pretzel: optimized Machine Learning framework for low-latency and high throug...Pretzel: optimized Machine Learning framework for low-latency and high throug...
Pretzel: optimized Machine Learning framework for low-latency and high throug...NECST Lab @ Politecnico di Milano
 
Object Detection & Machine Learning Paper
 Object Detection & Machine Learning Paper Object Detection & Machine Learning Paper
Object Detection & Machine Learning PaperJoseph Mogannam
 
Mini Project final report on " LEAKY BUCKET ALGORITHM "
Mini Project final report on " LEAKY BUCKET ALGORITHM "Mini Project final report on " LEAKY BUCKET ALGORITHM "
Mini Project final report on " LEAKY BUCKET ALGORITHM "Nikhil Jain
 
OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...
OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...
OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...ICS
 
Efficient and Advanced Omniscient Debugging for xDSMLs (SLE 2015)
Efficient and Advanced Omniscient Debugging for xDSMLs (SLE 2015)Efficient and Advanced Omniscient Debugging for xDSMLs (SLE 2015)
Efficient and Advanced Omniscient Debugging for xDSMLs (SLE 2015)Benoit Combemale
 
VitaFlow | Mageswaran Dhandapani [Pramati]
VitaFlow | Mageswaran Dhandapani [Pramati]VitaFlow | Mageswaran Dhandapani [Pramati]
VitaFlow | Mageswaran Dhandapani [Pramati]Pramati Technologies
 
Hivemall meets Digdag @Hackertackle 2018-02-17
Hivemall meets Digdag @Hackertackle 2018-02-17Hivemall meets Digdag @Hackertackle 2018-02-17
Hivemall meets Digdag @Hackertackle 2018-02-17Makoto Yui
 
MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle Databricks
 
Code Difference Visualization by a Call Tree
Code Difference Visualization by a Call TreeCode Difference Visualization by a Call Tree
Code Difference Visualization by a Call TreeKamiya Toshihiro
 
DDD on example of Symfony (SfCampUA14)
DDD on example of Symfony (SfCampUA14)DDD on example of Symfony (SfCampUA14)
DDD on example of Symfony (SfCampUA14)Oleg Zinchenko
 
Fine tuning large LMs
Fine tuning large LMsFine tuning large LMs
Fine tuning large LMsSylvainGugger
 

Similar to Generative AI for Reengineering Variants into Software Product Lines: An Experience Report (20)

Directive-based approach to Heterogeneous Computing
Directive-based approach to Heterogeneous ComputingDirective-based approach to Heterogeneous Computing
Directive-based approach to Heterogeneous Computing
 
Move from C to Go
Move from C to GoMove from C to Go
Move from C to Go
 
EclipseCon Eu 2015 - Breathe life into your Designer!
EclipseCon Eu 2015 - Breathe life into your Designer!EclipseCon Eu 2015 - Breathe life into your Designer!
EclipseCon Eu 2015 - Breathe life into your Designer!
 
SiriusCon 2015 - Breathe Life into Your Designer!
SiriusCon 2015 - Breathe Life into Your Designer!SiriusCon 2015 - Breathe Life into Your Designer!
SiriusCon 2015 - Breathe Life into Your Designer!
 
resume
resumeresume
resume
 
Fast Insights to Optimized Vectorization and Memory Using Cache-aware Rooflin...
Fast Insights to Optimized Vectorization and Memory Using Cache-aware Rooflin...Fast Insights to Optimized Vectorization and Memory Using Cache-aware Rooflin...
Fast Insights to Optimized Vectorization and Memory Using Cache-aware Rooflin...
 
PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems
PRETZEL: Opening the Black Box of Machine Learning Prediction Serving SystemsPRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems
PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems
 
Advanced Graphics Workshop - GFX2011
Advanced Graphics Workshop - GFX2011Advanced Graphics Workshop - GFX2011
Advanced Graphics Workshop - GFX2011
 
Pretzel: optimized Machine Learning framework for low-latency and high throug...
Pretzel: optimized Machine Learning framework for low-latency and high throug...Pretzel: optimized Machine Learning framework for low-latency and high throug...
Pretzel: optimized Machine Learning framework for low-latency and high throug...
 
Object Detection & Machine Learning Paper
 Object Detection & Machine Learning Paper Object Detection & Machine Learning Paper
Object Detection & Machine Learning Paper
 
Mini Project final report on " LEAKY BUCKET ALGORITHM "
Mini Project final report on " LEAKY BUCKET ALGORITHM "Mini Project final report on " LEAKY BUCKET ALGORITHM "
Mini Project final report on " LEAKY BUCKET ALGORITHM "
 
OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...
OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...
OpenGL Fixed Function to Shaders - Porting a fixed function application to “m...
 
Efficient and Advanced Omniscient Debugging for xDSMLs (SLE 2015)
Efficient and Advanced Omniscient Debugging for xDSMLs (SLE 2015)Efficient and Advanced Omniscient Debugging for xDSMLs (SLE 2015)
Efficient and Advanced Omniscient Debugging for xDSMLs (SLE 2015)
 
VitaFlow | Mageswaran Dhandapani [Pramati]
VitaFlow | Mageswaran Dhandapani [Pramati]VitaFlow | Mageswaran Dhandapani [Pramati]
VitaFlow | Mageswaran Dhandapani [Pramati]
 
Hivemall meets Digdag @Hackertackle 2018-02-17
Hivemall meets Digdag @Hackertackle 2018-02-17Hivemall meets Digdag @Hackertackle 2018-02-17
Hivemall meets Digdag @Hackertackle 2018-02-17
 
MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle MLFlow: Platform for Complete Machine Learning Lifecycle
MLFlow: Platform for Complete Machine Learning Lifecycle
 
Code Difference Visualization by a Call Tree
Code Difference Visualization by a Call TreeCode Difference Visualization by a Call Tree
Code Difference Visualization by a Call Tree
 
DDD on example of Symfony (SfCampUA14)
DDD on example of Symfony (SfCampUA14)DDD on example of Symfony (SfCampUA14)
DDD on example of Symfony (SfCampUA14)
 
Fine tuning large LMs
Fine tuning large LMsFine tuning large LMs
Fine tuning large LMs
 
Code generation
Code generationCode generation
Code generation
 

More from University of Rennes, INSA Rennes, Inria/IRISA, CNRS

More from University of Rennes, INSA Rennes, Inria/IRISA, CNRS (20)

A Demonstration of End-User Code Customization Using Generative AI
A Demonstration of End-User Code Customization Using Generative AIA Demonstration of End-User Code Customization Using Generative AI
A Demonstration of End-User Code Customization Using Generative AI
 
24 Reasons Why Variability Models Are Not Yet Universal (24RWVMANYU)
24 Reasons Why Variability Models Are Not Yet Universal (24RWVMANYU)24 Reasons Why Variability Models Are Not Yet Universal (24RWVMANYU)
24 Reasons Why Variability Models Are Not Yet Universal (24RWVMANYU)
 
On Programming Variability with Large Language Model-based Assistant
On Programming Variability with Large Language Model-based AssistantOn Programming Variability with Large Language Model-based Assistant
On Programming Variability with Large Language Model-based Assistant
 
Tackling Deep Software Variability Together
Tackling Deep Software Variability TogetherTackling Deep Software Variability Together
Tackling Deep Software Variability Together
 
On anti-cheating in chess, science, reproducibility, and variability
On anti-cheating in chess, science, reproducibility, and variabilityOn anti-cheating in chess, science, reproducibility, and variability
On anti-cheating in chess, science, reproducibility, and variability
 
Feature Subset Selection for Learning Huge Configuration Spaces: The case of ...
Feature Subset Selection for Learning Huge Configuration Spaces: The case of ...Feature Subset Selection for Learning Huge Configuration Spaces: The case of ...
Feature Subset Selection for Learning Huge Configuration Spaces: The case of ...
 
Machine Learning and Deep Software Variability
Machine Learning and Deep Software VariabilityMachine Learning and Deep Software Variability
Machine Learning and Deep Software Variability
 
Mastering Software Variability for Innovation and Science
Mastering Software Variability for Innovation and ScienceMastering Software Variability for Innovation and Science
Mastering Software Variability for Innovation and Science
 
Transfer Learning Across Variants and Versions: The Case of Linux Kernel Size
Transfer Learning Across Variants and Versions: The Case of Linux Kernel SizeTransfer Learning Across Variants and Versions: The Case of Linux Kernel Size
Transfer Learning Across Variants and Versions: The Case of Linux Kernel Size
 
Reproducible Science and Deep Software Variability
Reproducible Science and Deep Software VariabilityReproducible Science and Deep Software Variability
Reproducible Science and Deep Software Variability
 
Software Variability and Artificial Intelligence
Software Variability and Artificial IntelligenceSoftware Variability and Artificial Intelligence
Software Variability and Artificial Intelligence
 
Teaching Software Product Lines: A Snapshot of Current Practices and Challenges
Teaching Software Product Lines: A Snapshot of Current Practices and ChallengesTeaching Software Product Lines: A Snapshot of Current Practices and Challenges
Teaching Software Product Lines: A Snapshot of Current Practices and Challenges
 
Exploiting the Enumeration of All Feature Model Configurations: A New Perspec...
Exploiting the Enumeration of All Feature Model Configurations: A New Perspec...Exploiting the Enumeration of All Feature Model Configurations: A New Perspec...
Exploiting the Enumeration of All Feature Model Configurations: A New Perspec...
 
Assessing Product Line Derivation Operators Applied to Java Source Code: An E...
Assessing Product Line Derivation Operators Applied to Java Source Code: An E...Assessing Product Line Derivation Operators Applied to Java Source Code: An E...
Assessing Product Line Derivation Operators Applied to Java Source Code: An E...
 
Synthesis of Attributed Feature Models From Product Descriptions
Synthesis of Attributed Feature Models From Product DescriptionsSynthesis of Attributed Feature Models From Product Descriptions
Synthesis of Attributed Feature Models From Product Descriptions
 
From Basic Variability Models to OpenCompare.org
From Basic Variability Models to OpenCompare.orgFrom Basic Variability Models to OpenCompare.org
From Basic Variability Models to OpenCompare.org
 
Pandoc: a universal document converter
Pandoc: a universal document converterPandoc: a universal document converter
Pandoc: a universal document converter
 
Metamorphic Domain-Specific Languages
Metamorphic Domain-Specific LanguagesMetamorphic Domain-Specific Languages
Metamorphic Domain-Specific Languages
 
3D Printing, Customization, and Product Lines
3D Printing, Customization, and Product Lines3D Printing, Customization, and Product Lines
3D Printing, Customization, and Product Lines
 
WebFML: Synthesizing Feature Models Everywhere (@ SPLC 2014)
WebFML: Synthesizing Feature Models Everywhere (@ SPLC 2014)WebFML: Synthesizing Feature Models Everywhere (@ SPLC 2014)
WebFML: Synthesizing Feature Models Everywhere (@ SPLC 2014)
 

Recently uploaded

Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsUnveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsAlberto González Trastoy
 
DNT_Corporate presentation know about us
DNT_Corporate presentation know about usDNT_Corporate presentation know about us
DNT_Corporate presentation know about usDynamic Netsoft
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...ICS
 
EY_Graph Database Powered Sustainability
EY_Graph Database Powered SustainabilityEY_Graph Database Powered Sustainability
EY_Graph Database Powered SustainabilityNeo4j
 
cybersecurity notes for mca students for learning
cybersecurity notes for mca students for learningcybersecurity notes for mca students for learning
cybersecurity notes for mca students for learningVitsRangannavar
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVshikhaohhpro
 
chapter--4-software-project-planning.ppt
chapter--4-software-project-planning.pptchapter--4-software-project-planning.ppt
chapter--4-software-project-planning.pptkotipi9215
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...kellynguyen01
 
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASEBATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASEOrtus Solutions, Corp
 
Engage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The UglyEngage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The UglyFrank van der Linden
 
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...stazi3110
 
Building Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop SlideBuilding Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop SlideChristina Lin
 
Project Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanationProject Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanationkaushalgiri8080
 
Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)OPEN KNOWLEDGE GmbH
 
What is Binary Language? Computer Number Systems
What is Binary Language?  Computer Number SystemsWhat is Binary Language?  Computer Number Systems
What is Binary Language? Computer Number SystemsJheuzeDellosa
 
Adobe Marketo Engage Deep Dives: Using Webhooks to Transfer Data
Adobe Marketo Engage Deep Dives: Using Webhooks to Transfer DataAdobe Marketo Engage Deep Dives: Using Webhooks to Transfer Data
Adobe Marketo Engage Deep Dives: Using Webhooks to Transfer DataBradBedford3
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comFatema Valibhai
 
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfjoe51371421
 
Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...OnePlan Solutions
 

Recently uploaded (20)

Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time ApplicationsUnveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications
 
DNT_Corporate presentation know about us
DNT_Corporate presentation know about usDNT_Corporate presentation know about us
DNT_Corporate presentation know about us
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
 
EY_Graph Database Powered Sustainability
EY_Graph Database Powered SustainabilityEY_Graph Database Powered Sustainability
EY_Graph Database Powered Sustainability
 
cybersecurity notes for mca students for learning
cybersecurity notes for mca students for learningcybersecurity notes for mca students for learning
cybersecurity notes for mca students for learning
 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTV
 
chapter--4-software-project-planning.ppt
chapter--4-software-project-planning.pptchapter--4-software-project-planning.ppt
chapter--4-software-project-planning.ppt
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
 
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASEBATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
BATTLEFIELD ORM: TIPS, TACTICS AND STRATEGIES FOR CONQUERING YOUR DATABASE
 
Engage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The UglyEngage Usergroup 2024 - The Good The Bad_The Ugly
Engage Usergroup 2024 - The Good The Bad_The Ugly
 
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
Building a General PDE Solving Framework with Symbolic-Numeric Scientific Mac...
 
Building Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop SlideBuilding Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
Building Real-Time Data Pipelines: Stream & Batch Processing workshop Slide
 
Project Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanationProject Based Learning (A.I).pptx detail explanation
Project Based Learning (A.I).pptx detail explanation
 
Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)Der Spagat zwischen BIAS und FAIRNESS (2024)
Der Spagat zwischen BIAS und FAIRNESS (2024)
 
What is Binary Language? Computer Number Systems
What is Binary Language?  Computer Number SystemsWhat is Binary Language?  Computer Number Systems
What is Binary Language? Computer Number Systems
 
Adobe Marketo Engage Deep Dives: Using Webhooks to Transfer Data
Adobe Marketo Engage Deep Dives: Using Webhooks to Transfer DataAdobe Marketo Engage Deep Dives: Using Webhooks to Transfer Data
Adobe Marketo Engage Deep Dives: Using Webhooks to Transfer Data
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.com
 
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Naraina Delhi 💯Call Us 🔝8264348440🔝
 
why an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdfwhy an Opensea Clone Script might be your perfect match.pdf
why an Opensea Clone Script might be your perfect match.pdf
 
Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...
 

Generative AI for Reengineering Variants into Software Product Lines: An Experience Report

  • 1. 1
  • 2. 2
  • 3. Variants of code (e.g., Java or C) Variants of user interfaces Variants of video sequences Variants of models (e.g., UML or SysML) Variants of « things » (3D models) … Variability Models (feature models) Reverse engineering variability and reusable assets e4CompareFramework ECCO tool 3
  • 4. Problem: Given a set of variants, how to synthesize a program that can be configured to retrieve original variants? ????????? 4
  • 5. Problem: Given a set of variants, how to synthesize a program that can be configured to retrieve original variants? SPL = feature model + annotated program (eg template-based generator) Expected properties: soundness/completeness/meaningful set of features (for configuration or maintenance/evolution/expansion) Reverse engineering variability and reusable assets Error-prone Time-consuming e4CompareFramework ECCO tool 5
  • 6. Problem: Given a set of variants, how to synthesize a program that can be configured to retrieve original variants? SPL = feature model + annotated program (eg template-based generator) Expected properties: soundness/completeness/meaningful set of features (for configuration or maintenance/evolution/expansion) Hypothesis: large language models (LLMs) can assist domain experts and developers in some re-engineering activities Error-prone Time-consuming 6
  • 7. Research method LLM = ChatGPT4 (no API) Session: sequence of prompts until getting a result Within a session, we, as users, asked for different tasks such as: ● domain analysis, summary of commonalities and differences, as plain languages or as tables, ● identification of features, ● synthesis of an integrated, 150% model or code (and possibly a ● visualization) ● synthesis of a template-based generator ● refactoring of models or code, corrections of code, model, or explanations that were perceived as inaccurate or simply unusable. Highly-interactive Repetition of some sessions (with some prompts’ variations) Qualitative assessment 7
  • 8. Research method: 5 cases with ChatGPT4 We consider five cases: ● Java variants ● UML variants ● state chart variants ● state machine variants ● PNG image variants We revisit some of the cases considered by https://github.com/but4reuse/but4reuse/wiki/Examples, this time with generative AI Qualitative assessment e4CompareFramework ECCO tool 8
  • 9. Case #1: BANKING SYSTEMS VARIANTS IN JAVA 9
  • 10. 10
  • 11. 11
  • 12. 12
  • 13. 13
  • 14. Case #2: BANKING SYSTEMS VARIANTS IN UML 14
  • 15. Case #2: BANKING SYSTEMS VARIANTS IN UML 15
  • 18. Case #4: STATECHARTS VARIANTS 18
  • 19. Case #5: PGN VARIANTS With current LLMs, we confirm (1) the impossibility to analyze PNG, binary files and compute a relevant diff – there are no magical solutions involved; (2) the provision of pixels location to LLM does not scale: there is simply too much information to fed in; (3) LLM is not helpful to find meaningful features: the information is too low-level and there is no semantic to infer. 19
  • 20. Discussion Limitations: ● size of input variants ○ Limited context-window and long-term memory ○ Impossible to fed a large XML file or an entire project (eg ArgoUML case) ● inaccuracies ○ See eg Case 2 ● similarity function can work “out of the box” (language agnostic) ● …but we know that similarity function is usually highly specific to a programming/modelling languages Threats: prompts used, LLM (= ChatGPT4) Challenge: a re-engineering benchmark for generative AI/LLM 20
  • 21. Problem: Given a set of variants, how to synthesize a program that can be configured to retrieve original variants? Positive and negative experiences Potential: automation of template synthesis, feature identification/naming, refactoring, etc. Strong limitations: prompt sensitivity, size of the input, inaccuracies Instead of thinking of ChatGPT as a replacement of BUT4Reuse or similar frameworks, the integration of both could be a more beneficial solution for the moment. Error-prone Time-consuming Hypothesis: large language models (LLMs) can assist domain experts and developers in some re-engineering activities 21
  • 23. I’d like to change the color of the cat’s tail On programming variability with LLMs Here is a TikZ code: tikzset{% cat/.pic={ tikzset{x=3cm/5,y=3cm/5,shift={(0,-1/3)}} useasboundingbox (-1,-1) (1,2); fill [BlueGrey900] (0,-2) .. controls ++(180:3) and ++(0:5/4) .. (-2,0) arc (270:90:1/5) .. controls ++(0:2) and ++(180:11/4) .. (0,-2+2/5); foreach i in {-1,1} scoped[shift={(1/2*i,9/4)}, rotate=45*i]{ clip [overlay] (0, 5/9) ellipse [radius=8/9]; clip [overlay] (0,-5/9) ellipse [radius=8/9]; fill [BlueGrey900] ellipse [radius=1]; clip [overlay] (0, 7/9) ellipse [radius=10/11]; clip [overlay] (0,-7/9) ellipse [radius=10/11]; fill [Purple100] ellipse [radius=1]; }; fill [BlueGrey900] ellipse [x radius=3/4, y radius=2]; fill [BlueGrey100] ellipse [x radius=1/3, y radius=1]; fill [BlueGrey900] (0,15/8) ellipse [x radius=1, y radius=5/6] (0, 8/6) ellipse [x radius=1/2, y radius=1/2] {[shift={(-1/2,-2)}, rotate= 10] ellipse [x radius=1/3, y radius=5/4]} {[shift={( 1/2,-2)}, rotate=-10] ellipse [x radius=1/3, y radius=5/4]}; fill [BlueGrey500] (-1/9,11/8) ellipse [x radius=1/5, y radius=1/5] ( 1/9,11/8) ellipse [x radius=1/5, y radius=1/5]; fill [Purple100] (0,12/8) ellipse [x radius=1/10, y radius=1/5] (0,12/8+1/9) ellipse [x radius=1/5 , y radius=1/10]; foreach i in {-1,1} scoped[shift={(1/2*i,2)}, rotate=35*i]{ clip [overlay] (0, 1/7) ellipse [radius=2/7]; clip [overlay] (0,-1/7) ellipse [radius=2/7]; fill [Yellow50] ellipse [radius=1]; }; scoped{ clip (-1,-2) rectangle ++(2,1); fill [BlueGrey900] (0,-2) ellipse [radius=1/2]; fill [Grey100] (-1/2,-2) ellipse [x radius=1/3, y radius=1/4] ( 1/2,-2) ellipse [x radius=1/3, y radius=1/4]; }; foreach i in {-1,1} 23
  • 26. Code synthesis with LLMs vs Codex https://arxiv.org/abs/2210.14699 26
  • 27. Generative programming [Czarnecki2000], Model-driven engineering: automatically generate variants from a specification written in one or more textual or graphical domain-specific languages Accidental and essential complexity Variability further increases this software complexity: multiple features, code variations, and an exponential number of possible variants 27
  • 28. LLM Hypothesis: Large language models (LLMs) act as a new variability compiler capable of transforming a high-level specification (“prompt”) into variable code, features, generators, configurable systems, etc. written in a given technological space. Motto: “features as prompts” 28