FORGE 2024
Sun 14 Apr 2024 Lisbon, Portugal
co-located with ICSE 2024

Welcome to the website of the special event of AI Foundation Models and Software Engineering (FORGE 2024) in ICSE 2024!

The AI Foundation Models and Software Engineering event aims to bring researchers, practitioners, and educators from the AI and Software Engineering community to solve the new challenges that we meet in the era of foundation models.

Foundation models (e.g., ChatGPT and Llama) have attracted great attention from both academia and industry. In Software Engineering, several studies showed that Large-Language Models (LLMs) achieved remarkable performance in various tasks, including code generation, testing, code review, and program repair. Recently, many LLM-based development tools have been released to improve software development and show great potential, for example, GitHub Copilot and Amazon CodeWhisperer.

FORGE aims to bring together researchers and practitioners to explore new frontiers in using foundation models on SE tasks, boost software development productivity, and improve code quality.

Forge 2024 will be held on Sunday, April 14, 2024, in Lisbon, Portugal.

Tracks
Plenary
You're viewing the program in a time zone which is different from your device's time zone change time zone

Sun 14 Apr

Displayed time zone: Lisbon change

09:00 - 10:30
FORGE2024 Opening / Keynote 1 / PanelKeynotes / Panel at Luis de Freitas Branco
Chair(s): Xin Xia Huawei Technologies, Xing Hu Zhejiang University
09:00
10m
Day opening
Introduction from The Chairs
Keynotes

09:10
40m
Keynote
Keynote 1: Large Language Models for Test Case Repair
Keynotes
Lionel Briand University of Ottawa, Canada; Lero centre, University of Limerick, Ireland
09:50
40m
Panel
Theme: Is There Space for Software Engineering Researchers to Contribute to AI4SE in The Era of Foundation Models?
Panel
Lionel Briand University of Ottawa, Canada; Lero centre, University of Limerick, Ireland, Denys Poshyvanyk William & Mary, Prem Devanbu University of California at Davis, Massimiliano Di Penta University of Sannio, Italy, David Lo Singapore Management University
10:30 - 11:00
Coffee BreakICSE Catering at Open Space
10:30
30m
Coffee break
Break
ICSE Catering

11:00 - 12:30
Foundation Models for Software Quality AssuranceResearch Track at Luis de Freitas Branco
Chair(s): Matteo Ciniselli Università della Svizzera Italiana
11:00
14m
Full-paper
Deep Multiple Assertions GenerationFull Paper
Research Track
Hailong Wang Zhejiang University, Tongtong Xu Huawei, Bei Wang Huawei
11:14
14m
Full-paper
MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented GenerationFull Paper
Research Track
Guanyu Wang Beijing University of Posts and Telecommunications, Yuekang Li The University of New South Wales, Yi Liu Nanyang Technological University, Gelei Deng Nanyang Technological University, Li Tianlin Nanyang Technological University, Guosheng Xu Beijing University of Posts and Telecommunications, Yang Liu Nanyang Technological University, Haoyu Wang Huazhong University of Science and Technology, Kailong Wang Huazhong University of Science and Technology
11:28
14m
Full-paper
Planning to Guide LLM for Code Coverage PredictionFull Paper
Research Track
Hridya Dhulipala University of Texas at Dallas, Aashish Yadavally University of Texas at Dallas, Tien N. Nguyen University of Texas at Dallas
11:42
7m
Short-paper
The Emergence of Large Language Models in Static Analysis: A First Look through Micro-BenchmarksNew Idea Paper
Research Track
Ashwin Prasad Shivarpatna Venkatesh University of Paderborn, Samkutty Sabu University of Paderborn, Amir Mir Delft University of Technology, Sofia Reis Instituto Superior Técnico, U. Lisboa & INESC-ID, Eric Bodden
11:49
14m
Full-paper
Reality Bites: Assessing the Realism of Driving Scenarios with Large Language ModelsFull Paper
Research Track
Jiahui Wu Simula Research Laboratory and University of Oslo, Chengjie Lu Simula Research Laboratory and University of Oslo, Aitor Arrieta Mondragon University, Tao Yue Beihang University, Shaukat Ali Simula Research Laboratory and Oslo Metropolitan University
12:03
7m
Short-paper
Assessing the Impact of GPT-4 Turbo in Generating Defeaters for Assurance CasesNew Idea Paper
Research Track
Kimya Khakzad Shahandashti York University, Mithila Sivakumar York University, Mohammad Mahdi Mohajer York University, Alvine Boaye Belle York University, Song Wang York University, Timothy Lethbridge University of Ottawa
12:10
20m
Other
Discussion
Research Track

12:30 - 14:00
12:30
90m
Lunch
Lunch
ICSE Catering

14:00 - 15:30
Keynote 2 & Properties of Foundation ModelsResearch Track / Keynotes at Luis de Freitas Branco
Chair(s): David Lo Singapore Management University, Feifei Niu Nanjing University
14:00
40m
Keynote
Keynote 2: Towards an Interpretable Science of Deep Learning for Software Engineering: A Causal Inference View
Keynotes
Denys Poshyvanyk William & Mary
14:40
14m
Full-paper
Exploring the Impact of the Output Format on the Evaluation of Large Language Models for Code TranslationFull Paper
Research Track
Marcos Macedo Queen's University, Kingston, Ontario, Yuan Tian Queen's University, Kingston, Ontario, Filipe Cogo Huawei, Bram Adams Queen's University
Pre-print
14:54
7m
Short-paper
Is Attention All You Need? Toward a Conceptual Model for Social Awareness in Large Language ModelsNew Idea Paper
Research Track
Gianmario Voria University of Salerno, Gemma Catolino University of Salerno, Fabio Palomba University of Salerno
Pre-print
15:01
14m
Full-paper
An Exploratory Investigation into Code License Infringements in Large Language Model Training DatasetsFull Paper
Research Track
Jonathan Katzy Delft University of Technology, Răzvan Mihai Popescu Delft University of Technology, Arie van Deursen Delft University of Technology, Maliheh Izadi Delft University of Technology
15:15
15m
Other
Discussion
Research Track

15:30 - 16:00
Coffee BreakICSE Catering at Open Space
15:30
30m
Coffee break
Break
ICSE Catering

16:00 - 17:30
FORGE2024 Awards & Foundation Models for Code and Documentation GenerationResearch Track at Luis de Freitas Branco
Chair(s): Antonio Mastropaolo Università della Svizzera italiana
16:00
10m
Awards
Award Ceremony
Research Track

16:10
7m
Short-paper
Fine Tuning Large Language Model for Secure Code GenerationNew Idea Paper
Research Track
Junjie Li Concordia University, Aseem Sangalay Delhi Technological University, Cheng Cheng Concordia University, Yuan Tian Queen's University, Kingston, Ontario, Jinqiu Yang Concordia University
16:17
14m
Full-paper
Investigating the Performance of Language Models for Completing Code in Functional Programming Languages: a Haskell Case StudyFull Paper
Research Track
Tim van Dam Delft University of Technology, Frank van der Heijden Delft University of Technology, Philippe de Bekker Delft University of Technology, Berend Nieuwschepen Delft University of Technology, Marc Otten Delft University of Technology, Maliheh Izadi Delft University of Technology
16:31
7m
Short-paper
On Evaluating the Efficiency of Source Code Generated by LLMsNew Idea Paper
Research Track
Changan Niu Software Institute, Nanjing University, Ting Zhang Singapore Management University, Chuanyi Li Nanjing University, Bin Luo Nanjing University, Vincent Ng Human Language Technology Research Institute, University of Texas at Dallas, Richardson, TX 75083-0688
16:38
14m
Full-paper
PathOCL: Path-Based Prompt Augmentation for OCL Generation with GPT-4Full Paper
Research Track
Seif Abukhalaf Polytechnique Montreal, Mohammad Hamdaqa Polytechnique Montréal, Foutse Khomh École Polytechnique de Montréal
16:52
7m
Short-paper
Creative and Correct: Requesting Diverse Code Solutions from AI Foundation ModelsNew Idea Paper
Research Track
Scott Blyth Monash University, Christoph Treude Singapore Management University, Markus Wagner Monash University, Australia
16:59
7m
Short-paper
Commit Message Generation via ChatGPT: How Far Are We?New Idea Paper
Research Track
Yifan Wu Peking University, Ying Li School of Software and Microelectronics, Peking University, Beijing, China, Siyu Yu The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)
17:06
24m
Other
Discussion
Research Track

Accepted Papers

Title
An Exploratory Investigation into Code License Infringements in Large Language Model Training DatasetsFull Paper
Research Track
Assessing the Impact of GPT-4 Turbo in Generating Defeaters for Assurance CasesNew Idea Paper
Research Track
Commit Message Generation via ChatGPT: How Far Are We?New Idea Paper
Research Track
Creative and Correct: Requesting Diverse Code Solutions from AI Foundation ModelsNew Idea Paper
Research Track
Deep Multiple Assertions GenerationFull Paper
Research Track
Discussion
Research Track

Discussion
Research Track

Discussion
Research Track

Exploring the Impact of the Output Format on the Evaluation of Large Language Models for Code TranslationFull Paper
Research Track
Pre-print
Fine Tuning Large Language Model for Secure Code GenerationNew Idea Paper
Research Track
Investigating the Performance of Language Models for Completing Code in Functional Programming Languages: a Haskell Case StudyFull Paper
Research Track
Is Attention All You Need? Toward a Conceptual Model for Social Awareness in Large Language ModelsNew Idea Paper
Research Track
Pre-print
MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented GenerationFull Paper
Research Track
On Evaluating the Efficiency of Source Code Generated by LLMsNew Idea Paper
Research Track
PathOCL: Path-Based Prompt Augmentation for OCL Generation with GPT-4Full Paper
Research Track
Planning to Guide LLM for Code Coverage PredictionFull Paper
Research Track
Reality Bites: Assessing the Realism of Driving Scenarios with Large Language ModelsFull Paper
Research Track
The Emergence of Large Language Models in Static Analysis: A First Look through Micro-BenchmarksNew Idea Paper
Research Track

Call for Papers

The special event of AI Foundation Models and Software Engineering (FORGE 2024) in ICSE 2024 aims to bring researchers, practitioners, and educators from the AI and Software Engineering community to solve the new challenges that we meet in the era of foundation models.

Foundation models (e.g., ChatGPT and Llama) have attracted great attention from both academia and industry. In Software Engineering, several studies showed that Large-Language Models (LLMs) achieved remarkable performance in various tasks, including code generation, testing, code review, and program repair. Recently, many LLM-based development tools have been released to improve software development and show great potential, for example, GitHub Copilot and Amazon CodeWhisperer.

FORGE aims to bring together researchers and practitioners to explore new frontiers in using foundation models on SE tasks, boost software development productivity, and improve code quality.

FORGE 2024 will be held on Sunday, April 14, 2024, in Lisbon, Portugal.

Topic of Interests

We solicit submissions describing original and unpublished results of theoretical, empirical, conceptual, and experimental software engineering research related to Software Engineering with Foundation Models. Topics of interest include but are not limited to:

  1. FM for Requirement Engineering and Software Design
  2. FM for Code Generation/Reuse
  3. FM for Software Quality Assurance (e.g., including code review, analysis, testing, and debugging)
  4. FM to support software evolution (e.g., refactoring, technical debt management)
  5. FM for Software Security and Privacy
  6. FM for AIOps
  7. FM for software supply chain management, e.g., FM-based vulnerability identification, software composition analysis
  8. LLM Agents for SE tasks, e.g., how to use various FMs (e.g., LangChain) to complete a SE task.
  9. Prompt Engineering for Software Development
  10. Legal Aspects of using FM

Awards

The best papers will be awarded with an ACM SIGSOFT Distinguished Paper Award at FORGE. A selection of the best papers will be invited to a Special Issue of Empirical Software Engineering (EMSE).

How to Submit

We accept both full and new idea papers:

  1. Full Papers are expected to present new techniques, and/or provide research results, and/or report industry/open-source practice when applying foundation models for SE, and should be evaluated in a scientific way. Full Paper must not exceed 10 pages for the main text, inclusive of all figures, tables, appendices, etc. Two more pages containing only references are permitted.

  2. New Idea Papers should present new ideas in the field, e.g., new directions or techniques that are not yet fully developed and/or evaluated, or visions that show the future of AI foundation models and SE. Accepted new idea papers will present their ideas in a short lightning talk. New Idea Paper must not exceed 4 pages for the main text, inclusive of all figures, tables, appendices, etc. Two more pages containing only references are permitted.

All submissions must be in PDF. The page limit is strict, and it will not be possible to purchase additional pages at any point in the process (including after acceptance).

Formatting instructions are available at https://www.acm.org/publications/proceedings-template for both LaTeX and Word users. LaTeX users must use the provided acmart.cls and ACM-Reference-Format.bst without modification, enable the conference format in the preamble of the document (i.e., \documentclass[sigconf,review]{acmart}), and use the ACM reference format for the bibliography (i.e., \bibliographystyle{ACM-Reference-Format}). The review option adds line numbers, thereby allowing referees to refer to specific lines in their comments.

Note, we use double-anonymous reviewing. Be sure to remove the list of authors from the submitted paper. If citing your own prior work, please do so in the third person to obscure the relationship you have with it. For advice, guidance, and explanation about the double-anonymous review process, see ICSE Research Track’s Q&A page.

By submitting your article to an ACM Publication, you are hereby acknowledging that you and your co-authors are subject to all ACM Publications Policies, including ACM’s new Publications Policy on Research Involving Human Participants and Subjects. Alleged violations of this policy or any ACM Publications Policy will be investigated by ACM and may result in a full retraction of your paper, in addition to other potential penalties, as per ACM Publications Policy.

Please ensure that you and your co-authors obtain an ORCID ID, so you can complete the publishing process for your accepted paper. ACM has been involved in ORCID from the start and we have recently made a commitment to collect ORCID IDs from all of our published authors. The collection process has started and will roll out as a requirement throughout 2022. We are committed to improving author discoverability, ensuring proper attribution, and contributing to ongoing community efforts around name normalization; your ORCID ID will help in these efforts.

All papers must be written in English.

All papers should be made accessible to people with disabilities. Some guidelines from the SIGACCESS community are available here: https://assets21.sigaccess.org/creating_accessible_pdfs.html.

Please submit your paper on HotCRP: https://forge-2024.hotcrp.com/

Review Criteria

Following the review criteria of ICSE 2024, each paper submitted to the FORGE 2024 will be evaluated based on the following criteria:

  1. Novelty: The novelty and innovativeness of contributed solutions, problem formulations, methodologies, theories, and/or evaluations, i.e., the extent to which the paper is sufficiently original with respect to the state-of-the-art.

  2. Rigor: The soundness, clarity, and depth of a technical or theoretical contribution, and the level of thoroughness and completeness of an evaluation.

  3. Relevance: The significance and/or potential impact of the research to the field of software engineering.

  4. Verifiability and Transparency: The extent to which the paper includes sufficient information to understand how an innovation works; to understand how data was obtained, analyzed, and interpreted; and how the paper supports independent verification or replication of the paper’s claimed contributions. Any artifacts attached to or linked from the paper may be checked by one reviewer.

  5. Presentation: The clarity of the exposition in the paper.

Reviewers will carefully consider all of the above criteria during the review process, and authors should take great care in clearly addressing them all. The paper should clearly explain and justify the claimed contributions.