@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}

}

@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}

}

@inproceedings{TomaCAIN2024,

title = {An Exploratory Study of Dataset and Model Management in Open Source Machine Learning Applications},

author = {Tajkia Rahman Toma and Cor-Paul Bezemer},

year  = {2024},

date = {2024-01-17},

urldate = {2024-01-17},

booktitle = {3rd IEEE/ACM International Conference on AI Engineering - Software Engineering for AI (CAIN)},

pages = {1--11},

abstract = {Datasets and models are two key artifacts in machine learning

(ML) applications. Although there exist tools to support dataset

and model developers in managing ML artifacts, little is known

about how these datasets and models are integrated into ML ap-

plications. In this paper, we study how datasets and models in ML

applications are managed. In particular, we focus on how these

artifacts are stored and versioned alongside the applications. After

analyzing 93 repositories, we identified the most common storage

location to store datasets and models is the file system, which causes

availability issues. Notably, large data and model files, exceeding

approximately 60 MB, are stored exclusively in remote storage and

downloaded as needed. Most of the datasets and models lack proper

integration with the version control system, posing potential trace-

ability and reproducibility issues. Additionally, although datasets

and models are likely to evolve during the application development,

they are rarely updated in application repositories.},

keywords = {Data maintenance, SE4ML},

pubstate = {published},

tppubtype = {inproceedings}

}