The Software Development Life Cycle (SDLC) governs the creation of software systems, encompassing various engineering phases such as requirement specification, design, coding, testing, and maintenance. Software development is an effort-intensive and time-consuming activity whereas systems today need to reflect changes as quickly as possible. Most complex, large-scale software systems of today derive their requirements from existing (legacy) software and partial (incomplete) descriptions. Software development is thus a complex combination of transformation, reverse and forward engineering, involving code, data, and specifications, where data is both structured and unstructured. Expertise from subject matter specialists (SMEs) is essential at each phase, which brings in the important component of knowledge. While Model-Driven Engineering (MDE), Knowledge Engineering (KE), and Reverse Engineering (RE) have mitigated some of the challenges, the emergence of Generative AI techniques holds the potential for a substantial breakthrough. These techniques empower SMEs to construct purposeful engineering artifacts using natural language interactions.
The proposed workshop aims to provide a collaborative platform for researchers and practitioners to delve into the convergence of traditional MDE, KE, and RE methodologies together with Generative AI technologies. By synergizing the strengths of Gen AI, modeling, and knowledge representation for SDLC, our goal is to define a trajectory toward enhanced software engineering practices. We seek discussion on the following pivotal questions:
The workshop aims to foster interactive discussions, enabling participants to collectively shape the future of advanced software engineering. The inaugural edition will feature talks by invited speakers who are exploring one or more of the above questions, interspersed with short experiences of researchers who are exploring specific challenges of software engineering using GenAI techniques. Time permitting, we will have short lightening talks by researchers to share interesting observations and anecdotes.
Aditya Kanade Microsoft Research, India |
|
Dinesh Garg IBM Research, India |
|
Disha Shrivastava (Virtual talk) Google, UK |
|
Hridesh Rajan IOWA State University, USA |
|
Jyothi Vedurada IIT Hyderabad, India |
Leveraging Large Language Models for Effective Software Development Practices |
Vikrant Kaulgud Accenture Labs, India |
The Software Development Life Cycle (SDLC) governs the creation of software systems, encompassing different engineering phases such as requirement specification, design, coding, testing, and maintenance. Software development is an effort-intensive and time-consuming activity. Most complex, large-scale software systems of today derive their requirements from existing (legacy) software and partial (incomplete) descriptions. Thus, expertise from subject matter specialists (SMEs) is essential at each phase, which brings in the important component of knowledge. The emergence of Generative AI techniques holds the potential to empower SMEs to construct purposeful engineering artifacts using natural language interactions.
The workshop aims to provide a collaborative platform for researchers from academia, industry, and practitioners. Through this platform, we expect to delve into the convergence of Generative AI, Knowledge Engineering, MDE, Software Understanding, and Software Transformation.
We solicit submissions in the form of one-page (max 500 words) abstracts describing case studies, interesting experiments, best practices, and lessons learned while applying Generative AI to various SE areas, but not limited to the following topics:
Submission Information : Abstract should be original work in text format written in english not more than 500 words and submitted via the form. In case of any questions, you can write an email to GenAIForSE.ISECWorkshop@tcs.com
Acceptance criteria : Abstracts will be selected based on reviews by the workshop organizing committee. Criteria will be the clarity of articulation of the problem being solved, bringing out the specific need for Generative AI to solve the problem and the novelty of the approach. Authors of accepted abstracts will receive further instructions for submitting camera-ready presentations. At least one of the authors MUST register for the ISEC conference, and attend the conference in-person to present their exploration and innovation at the workshop.
Important Dates |
|
15 Dec 2023 |
Last date for submitting abstracts |
22 Dec 2023 |
Extended date for submitting abstracts |
8 Jan 2024 |
Notification of selected abstracts |
30 Jan 2024 |
Publishing list of accepted talks |
22 Feb 2024 |
GenAI4SE workshop |
Submission Link |
|
Schedule |
|||
Time |
Talk |
Speaker / Chair |
Topic |
8:45 AM |
Welcome |
R.D.Naik / Manasi Patwardhan |
Opening remarks and Agenda |
9:00 to 11:00 AM |
Session 1 |
Chair: Raveendra Kumar |
Software engineering at scale |
9:00 AM |
Invited talk 1 |
Aditya Kanade, Microsoft Research |
Making LLMs Usable in Large-scale Software Engineering |
9:35 AM |
Invited talk 2 |
Dinesh Garg, IBM Research |
Generative AI for Cobol-to-Java Translation |
10:10 AM |
Abstract 1 |
Rudra Dhar, IIITH, PhD student |
Exploring the Capability of LLMs in generating Architectural Design Decision |
10:25 AM |
Abstract 2 |
Loghamaniya A, Sona College Tech, Salem, UG student |
Revolutionizing Software Development : The Synergy of AI in Requirement Management |
10:40 AM |
Q&A |
Moderated by Raveendra Kumar |
Interaction with all 4 speakers of the session |
11:00:00 AM : Tea Break |
|||
11:30 to 1:10 PM |
Session 2 |
Chair: Asha Rajbhoj |
LLMs for specific software engineering problems |
11:30 AM |
Invited talk 3 |
Jyoti Vedurada, IIT Hyderabad |
Leveraging Large Language Models for Effective Software Development Practices |
12:05 PM |
Abstract 3 |
Yasharth Bajpai, Microsoft |
AI assisted Code Debugging inside IDEs |
12:20 PM |
Abstract 4 |
Korraprolu Brahma Reddy, IIITH, PG student |
Testcase generation for requirements in natural language - an LLM Comparison study |
12:35 PM |
Q&A |
Moderated by Asha Rajbhoj |
Interaction with all 3 speakers of the session |
1:00:00 PM: Lunch Break |
|||
2:00 to 3:30 PM |
Session 3 |
Chair: Manasi Patwardhan |
|
2:00 PM |
Working group formation, discussion and experiments |
All participants |
Particpants to bring their laptops so that they can do small experiments using LLMs, based on the proposed topics, discuss amongst their respective group, and present their findings. Topics will be proposed on the day of the workshop. |
3:00 PM |
Presentations |
Moderated by Manasi Patwardhan |
Presentation of findings by each working group |
3:30:00 PM: Tea Break |
|||
4:00 to 6:00 PM |
Session 4 |
Chair: R.D.Naik |
Channelizing GenAI for software engineering |
4:00 PM |
Invited talk 5 |
Disha Shrivastava, Google Virtual Talk |
Effectively Utilizing Contextual Cues for LLMs of Code |
4:35 PM |
Abstract 5 |
Shubham Gandhi, TCS Research |
Unleashing large language models for precise and readable COBOL to Java translation |
4:50 PM |
Abstract 6 |
SujayKumar Reddy M, VIT Vellore, UG student |
RAG Based Documentation Generation from code files, A Case Study on LLM for open-source projects |
5:05 PM |
Abstract 7 |
Piyush Tillu, E&Y, IIT Khg |
Unleashing GenAI to the world of Internal Audits |
5:20 PM |
Interaction |
Moderated by R.D.Naik |
|
5:45 PM |
Closing Remarks |
Raveendra Kumar / Manasi Patwardhan |
He has 30+ years of industrial research experience, specializing in software engineering, meta-modelling, program analysis, text analysis, machine learning, GenAI. They excel in extracting domain specifications from legacy code and documents, applying expertise in software modernization, enterprise onboarding, and synthesizing new software systems. He has 20+ publications and 10+ patents to his credit.
She has over 27 years of experience in industrial research and her research interests include Generative AI, Requirement Engineering, Model-Driven Engineering, Meta-modelling, Software Engineering, Enterprise Modeling and Architecture, Artificial Intelligence, Natural Language Processing, Data Analytics and Business Process Modelling. She has over 20 publications and several patents to her credit.
She has over 18 years of experience in academic and industrial research, she specializes in Generative AI, AI for Code and Program Synthesis, Natural Language Understanding, Neuro-Symbolic systems, and Multi-Modal Multi-Lingual Processing. She has over 30 publications and 5 patents, and serves on the program committees of prestigious NLP conferences like ACL, EMNLP, and NAACL.
He has 27+ years of experience in software services delivery and related research, he specializes in application of Symbolic, Generative AI, and Neuro-symbolic techniques to transform software systems and enhance software testing methodologies. His expertise lies in leveraging advanced AI methods to revolutionize software development processes, ensuring efficiency, reliability, and innovation.
Please visit the ISEC Conference page for workshop location and registration.