AI alignment for ethical compliance and risk mitigation in industrial applications
(2025) In Lecture notes in computer science p.20-35- Abstract
- Context: AI technologies are increasingly embedded in products and software engineering processes of industrial IoT, autonomous systems, and cyber-physical systems. It is therefore essential to ensure alignment with safety, reliability, and ethical standards. However, practical software engineering methods for managing misalignment risks remain underdeveloped.
Objective: This study aims to explore industry awareness of misalignment risks and current practices for monitoring them within real-world software engineering contexts.
Method: We conducted seven interviews with industry professionals to examine perceptions of misalignment risks, gather insights into existing practices, and understand approaches to alignment... (More) - Context: AI technologies are increasingly embedded in products and software engineering processes of industrial IoT, autonomous systems, and cyber-physical systems. It is therefore essential to ensure alignment with safety, reliability, and ethical standards. However, practical software engineering methods for managing misalignment risks remain underdeveloped.
Objective: This study aims to explore industry awareness of misalignment risks and current practices for monitoring them within real-world software engineering contexts.
Method: We conducted seven interviews with industry professionals to examine perceptions of misalignment risks, gather insights into existing practices, and understand approaches to alignment across various industrial settings. Three recently proposed taxonomies guided our discussions: one on ethical guidelines for trustworthy AI published by the EU, another summarizing identified AI risks, and a third addressing “double-edged components” (aspects of AI systems that can simultaneously yield positive and negative effects.)
Results: Our analysis identified common misalignment risks across these settings and revealed limited use of dedicated testing or monitoring for AI alignment. Most organizations rely on general oversight rather than specialized tools.
Conclusion: These findings highlight the need to develop tailored governance practices for alignment in industrial software engineering settings. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/8f4d66bd-0438-4667-8081-773f101f73ca
- author
- Gupta, Rushali
LU
; Song, Qunying
; Wagner, Matthias
LU
; Engström, Emelie
LU
; Söderberg, Emma
LU
; Borg, Markus
and Runeson, Per
LU
- organization
-
- Software Engineering Research Group
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- NEXTG2COM – a Vinnova Competence Centre in Advanced Digitalisation
- LTH Profile Area: AI and Digitalization
- LTH School of Engineering in Helsingborg
- LU Profile Area: Natural and Artificial Cognition
- Information and Communications Engineering (M.Sc.Eng.)
- Department of Computer Science
- Software Development and Environments
- publishing date
- 2025-12-03
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Product-Focused Software Process Improvement : 26th International Conference, PROFES 2025, Salerno, Italy, December 1–3, 2025, Proceedings - 26th International Conference, PROFES 2025, Salerno, Italy, December 1–3, 2025, Proceedings
- series title
- Lecture notes in computer science
- editor
- Scanniello, Giuseppe ; Lenarduzzi, Valentina ; Romano, Simone ; Vegas, Sira and Francese, Rita
- issue
- 16361
- pages
- 16 pages
- publisher
- Springer
- external identifiers
-
- scopus:105023328961
- ISSN
- 16361
- 0302-9743
- ISBN
- 978-3-032-12089-2
- 978-3-032-12088-5
- DOI
- 10.1007/978-3-032-12089-2_2
- project
- AI Alignment through Continuous Operational Testing
- Next Generation Communication and Computational Infrastructures and Applications (NextG2Com)
- language
- English
- LU publication?
- yes
- id
- 8f4d66bd-0438-4667-8081-773f101f73ca
- date added to LUP
- 2025-12-09 11:03:00
- date last changed
- 2025-12-12 03:46:48
@inproceedings{8f4d66bd-0438-4667-8081-773f101f73ca,
abstract = {{Context: AI technologies are increasingly embedded in products and software engineering processes of industrial IoT, autonomous systems, and cyber-physical systems. It is therefore essential to ensure alignment with safety, reliability, and ethical standards. However, practical software engineering methods for managing misalignment risks remain underdeveloped. <br/><br/>Objective: This study aims to explore industry awareness of misalignment risks and current practices for monitoring them within real-world software engineering contexts. <br/><br/>Method: We conducted seven interviews with industry professionals to examine perceptions of misalignment risks, gather insights into existing practices, and understand approaches to alignment across various industrial settings. Three recently proposed taxonomies guided our discussions: one on ethical guidelines for trustworthy AI published by the EU, another summarizing identified AI risks, and a third addressing “double-edged components” (aspects of AI systems that can simultaneously yield positive and negative effects.) <br/><br/>Results: Our analysis identified common misalignment risks across these settings and revealed limited use of dedicated testing or monitoring for AI alignment. Most organizations rely on general oversight rather than specialized tools. <br/><br/>Conclusion: These findings highlight the need to develop tailored governance practices for alignment in industrial software engineering settings.}},
author = {{Gupta, Rushali and Song, Qunying and Wagner, Matthias and Engström, Emelie and Söderberg, Emma and Borg, Markus and Runeson, Per}},
booktitle = {{Product-Focused Software Process Improvement : 26th International Conference, PROFES 2025, Salerno, Italy, December 1–3, 2025, Proceedings}},
editor = {{Scanniello, Giuseppe and Lenarduzzi, Valentina and Romano, Simone and Vegas, Sira and Francese, Rita}},
isbn = {{978-3-032-12089-2}},
issn = {{16361}},
language = {{eng}},
month = {{12}},
number = {{16361}},
pages = {{20--35}},
publisher = {{Springer}},
series = {{Lecture notes in computer science}},
title = {{AI alignment for ethical compliance and risk mitigation in industrial applications}},
url = {{http://dx.doi.org/10.1007/978-3-032-12089-2_2}},
doi = {{10.1007/978-3-032-12089-2_2}},
year = {{2025}},
}