Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Large Language Models for Printed Circuit Board Test Generation

Lidbäck, Albin and Larsson, Erik LU orcid (2025) 26th IEEE Latin-American Test Symposium (LATS2025)
Abstract
Testing printed circuit boards (PCBs) is an important part of the production process. The development and generation of tests is however a labour-intensive process that requires expertise and deep understanding of the PCB. As generative Artificial Intelligence in form of Large Language Models (LLMs) as evolved, we explore its use for PCBs test generation. The main question is: for a given design specification and a test specification, how well can LLMs do test generation, that is create a test description? Some other questions are as follows. Is there difference between various LLMs? What inputs are needed in addition to a design specification and a test specification? What about the quality of generated tests? Is the use of LLM suitable... (More)
Testing printed circuit boards (PCBs) is an important part of the production process. The development and generation of tests is however a labour-intensive process that requires expertise and deep understanding of the PCB. As generative Artificial Intelligence in form of Large Language Models (LLMs) as evolved, we explore its use for PCBs test generation. The main question is: for a given design specification and a test specification, how well can LLMs do test generation, that is create a test description? Some other questions are as follows. Is there difference between various LLMs? What inputs are needed in addition to a design specification and a test specification? What about the quality of generated tests? Is the use of LLM suitable for automation? And does design complexity matter? (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
2025 IEEE 26th Latin American Test Symposium (LATS)
pages
2 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
26th IEEE Latin-American Test Symposium (LATS2025)
conference dates
2025-03-11 - 2025-03-14
external identifiers
  • scopus:105004738377
language
English
LU publication?
yes
id
cf9fe76f-7d0b-4206-b1df-df51df5d79e8
date added to LUP
2025-02-13 09:43:55
date last changed
2025-06-10 04:42:54
@inproceedings{cf9fe76f-7d0b-4206-b1df-df51df5d79e8,
  abstract     = {{Testing printed circuit boards (PCBs) is an important part of the production process. The development and generation of tests is however a labour-intensive process that requires expertise and deep understanding of the PCB. As generative Artificial Intelligence in form of Large Language Models (LLMs) as evolved, we explore its use for PCBs test generation. The main question is: for a given design specification and a test specification, how well can LLMs do test generation, that is create a test description? Some other questions are as follows. Is there difference between various LLMs? What inputs are needed in addition to a design specification and a test specification? What about the quality of generated tests? Is the use of LLM suitable for automation? And does design complexity matter?}},
  author       = {{Lidbäck, Albin and Larsson, Erik}},
  booktitle    = {{2025 IEEE 26th Latin American Test Symposium (LATS)}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  title        = {{Large Language Models for Printed Circuit Board Test Generation}},
  year         = {{2025}},
}