(
= Paper PDF, 
= Presentation slides, 
= Presentation video)
1.
Hao Li; Cor-Paul Bezemer; Ahmed E. Hassan
Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models Inproceedings
International Conference on Software Engineering - Software Engineering in Practice (ICSE - SEIP) Track, 2025.
Files: 
Abstract | BibTeX | Tags: FM4SE, Foundation models, SE4AI, SE4FM, SE4ML
@inproceedings{Li_SEFM_blogs,
title = {Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models},
author = {Hao Li and Cor-Paul Bezemer and Ahmed E. Hassan},
year = {2025},
date = {2025-04-27},
booktitle = {International Conference on Software Engineering - Software Engineering in Practice (ICSE - SEIP) Track},
abstract = {Foundation models (FMs) such as large language
models (LLMs) have significantly impacted many fields, including
software engineering (SE). The interaction between SE and FMs
has led to the integration of FMs into SE practices (FM4SE)
and the application of SE methodologies to FMs (SE4FM). While
several literature surveys exist on academic contributions to these
trends, we are the first to provide a practitioner’s view. We
analyze 155 FM4SE and 997 SE4FM blog posts from leading
technology companies, leveraging an FM-powered surveying
approach to systematically label and summarize the discussed
activities and tasks. We observed that while code generation is the
most prominent FM4SE task, FMs are leveraged for many other
SE activities such as code understanding, summarization, and
API recommendation. The majority of blog posts on SE4FM are
about model deployment & operation, and system architecture
& orchestration. Although the emphasis is on cloud deployments,
there is a growing interest in compressing FMs and deploying
them on smaller devices such as edge or mobile devices. We
outline eight future research directions inspired by our gained
insights, aiming to bridge the gap between academic findings
and real-world applications. Our study not only enriches the
body of knowledge on practical applications of FM4SE and
SE4FM but also demonstrates the utility of FMs as a powerful
and efficient approach in conducting literature surveys within
technical and grey literature domains. Our dataset, results, code
and used prompts can be found in our online replication package
at https://zenodo.org/records/14563992.},
keywords = {FM4SE, Foundation models, SE4AI, SE4FM, SE4ML},
pubstate = {published},
tppubtype = {inproceedings}
}
Foundation models (FMs) such as large language
models (LLMs) have significantly impacted many fields, including
software engineering (SE). The interaction between SE and FMs
has led to the integration of FMs into SE practices (FM4SE)
and the application of SE methodologies to FMs (SE4FM). While
several literature surveys exist on academic contributions to these
trends, we are the first to provide a practitioner’s view. We
analyze 155 FM4SE and 997 SE4FM blog posts from leading
technology companies, leveraging an FM-powered surveying
approach to systematically label and summarize the discussed
activities and tasks. We observed that while code generation is the
most prominent FM4SE task, FMs are leveraged for many other
SE activities such as code understanding, summarization, and
API recommendation. The majority of blog posts on SE4FM are
about model deployment & operation, and system architecture
& orchestration. Although the emphasis is on cloud deployments,
there is a growing interest in compressing FMs and deploying
them on smaller devices such as edge or mobile devices. We
outline eight future research directions inspired by our gained
insights, aiming to bridge the gap between academic findings
and real-world applications. Our study not only enriches the
body of knowledge on practical applications of FM4SE and
SE4FM but also demonstrates the utility of FMs as a powerful
and efficient approach in conducting literature surveys within
technical and grey literature domains. Our dataset, results, code
and used prompts can be found in our online replication package
at https://zenodo.org/records/14563992.
models (LLMs) have significantly impacted many fields, including
software engineering (SE). The interaction between SE and FMs
has led to the integration of FMs into SE practices (FM4SE)
and the application of SE methodologies to FMs (SE4FM). While
several literature surveys exist on academic contributions to these
trends, we are the first to provide a practitioner’s view. We
analyze 155 FM4SE and 997 SE4FM blog posts from leading
technology companies, leveraging an FM-powered surveying
approach to systematically label and summarize the discussed
activities and tasks. We observed that while code generation is the
most prominent FM4SE task, FMs are leveraged for many other
SE activities such as code understanding, summarization, and
API recommendation. The majority of blog posts on SE4FM are
about model deployment & operation, and system architecture
& orchestration. Although the emphasis is on cloud deployments,
there is a growing interest in compressing FMs and deploying
them on smaller devices such as edge or mobile devices. We
outline eight future research directions inspired by our gained
insights, aiming to bridge the gap between academic findings
and real-world applications. Our study not only enriches the
body of knowledge on practical applications of FM4SE and
SE4FM but also demonstrates the utility of FMs as a powerful
and efficient approach in conducting literature surveys within
technical and grey literature domains. Our dataset, results, code
and used prompts can be found in our online replication package
at https://zenodo.org/records/14563992.
2.
Tajkia Rahman Toma; Balreet Grewal; Cor-Paul Bezemer
Answering User Questions about Machine Learning Models through Standardized Model Cards Inproceedings
International Conference on Software Engineering (ICSE), 2025.
Files:
Abstract | BibTeX | Tags: Hugging Face, Q&A communities, Q&A websites, SE4AI, SE4FM, SE4ML
@inproceedings{Toma_UserQuestions,
title = {Answering User Questions about Machine Learning Models through Standardized Model Cards},
author = {Tajkia Rahman Toma and Balreet Grewal and Cor-Paul Bezemer },
year = {2025},
date = {2025-04-27},
booktitle = {International Conference on Software Engineering (ICSE)},
abstract = {Reusing pre-trained machine learning models is
becoming very popular due to model hubs such as Hugging Face
(HF). However, similar to when reusing software, many issues
may arise when reusing an ML model. In many cases, users
resort to asking questions on discussion forums such as the HF
community forum. In this paper, we study how we can reduce the
community’s workload in answering these questions and increase
the likelihood that questions receive a quick answer. We analyze
11,278 discussions from the HF model community that contain
user questions about ML models. We focus on the effort spent
handling questions, the high-level topics of discussions, and the
potential for standardizing responses in model cards based on
a model card template. Our findings indicate that there is not
much effort involved in responding to user questions, however,
40.1% of the questions remain open without any response. A
topic analysis shows that discussions are more centered around
technical details on model development and troubleshooting,
indicating that more input from model providers is required. We
show that 42.5% of the questions could have been answered if the
model provider followed a standard model card template for the
model card. Based on our analysis, we recommend that model
providers add more development-related details on the model’s
architecture, algorithm, data preprocessing and training code in
existing documentation (sub)sections and add new (sub)sections
to the template to address common questions about model usage
and hardware requirements.},
keywords = {Hugging Face, Q&A communities, Q&A websites, SE4AI, SE4FM, SE4ML},
pubstate = {published},
tppubtype = {inproceedings}
}
Reusing pre-trained machine learning models is
becoming very popular due to model hubs such as Hugging Face
(HF). However, similar to when reusing software, many issues
may arise when reusing an ML model. In many cases, users
resort to asking questions on discussion forums such as the HF
community forum. In this paper, we study how we can reduce the
community’s workload in answering these questions and increase
the likelihood that questions receive a quick answer. We analyze
11,278 discussions from the HF model community that contain
user questions about ML models. We focus on the effort spent
handling questions, the high-level topics of discussions, and the
potential for standardizing responses in model cards based on
a model card template. Our findings indicate that there is not
much effort involved in responding to user questions, however,
40.1% of the questions remain open without any response. A
topic analysis shows that discussions are more centered around
technical details on model development and troubleshooting,
indicating that more input from model providers is required. We
show that 42.5% of the questions could have been answered if the
model provider followed a standard model card template for the
model card. Based on our analysis, we recommend that model
providers add more development-related details on the model’s
architecture, algorithm, data preprocessing and training code in
existing documentation (sub)sections and add new (sub)sections
to the template to address common questions about model usage
and hardware requirements.
becoming very popular due to model hubs such as Hugging Face
(HF). However, similar to when reusing software, many issues
may arise when reusing an ML model. In many cases, users
resort to asking questions on discussion forums such as the HF
community forum. In this paper, we study how we can reduce the
community’s workload in answering these questions and increase
the likelihood that questions receive a quick answer. We analyze
11,278 discussions from the HF model community that contain
user questions about ML models. We focus on the effort spent
handling questions, the high-level topics of discussions, and the
potential for standardizing responses in model cards based on
a model card template. Our findings indicate that there is not
much effort involved in responding to user questions, however,
40.1% of the questions remain open without any response. A
topic analysis shows that discussions are more centered around
technical details on model development and troubleshooting,
indicating that more input from model providers is required. We
show that 42.5% of the questions could have been answered if the
model provider followed a standard model card template for the
model card. Based on our analysis, we recommend that model
providers add more development-related details on the model’s
architecture, algorithm, data preprocessing and training code in
existing documentation (sub)sections and add new (sub)sections
to the template to address common questions about model usage
and hardware requirements.