ReqGPT: a fine-tuned large language model for generating requirements documents
Research output: Journal contributions › Conference article in journal › Research › peer-review
Standard
In: Proceedings of the Design Society, Vol. 5, 01.08.2025, p. 2741-2750.
Research output: Journal contributions › Conference article in journal › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - ReqGPT
T2 - 25th International Conference on Engineering Design, ICED 2025
AU - Schiller, Kata Amanda
AU - Haddad, Meno Said
AU - Seibel, Arthur
N1 - Publisher Copyright: © The Author(s) 2025.
PY - 2025/8/1
Y1 - 2025/8/1
N2 - Effective product development relies on creating a requirements document that defines the product's technical specifications, yet traditional methods are labor-intensive and depend heavily on expert input. Large language models (LLMs) offer the potential for automation but struggle with limitations in prompt engineering and contextual sensitivity. To overcome these challenges, we developed ReqGPT, a domain-specific LLM fine-tuned on Mistral-7B-Instruct-v0.2 using 107 curated requirements lists. ReqGPT employs a standardized prompt to generate high-quality documents and demonstrated superior performance over GPT-4 and Mistral in multiple criteria based on ISO 29148. Our results underscore ReqGPT's efficiency, accuracy, cost-effectiveness, and alignment with industry standards, making it an ideal choice for localized use and safeguarding data privacy in technical product development.
AB - Effective product development relies on creating a requirements document that defines the product's technical specifications, yet traditional methods are labor-intensive and depend heavily on expert input. Large language models (LLMs) offer the potential for automation but struggle with limitations in prompt engineering and contextual sensitivity. To overcome these challenges, we developed ReqGPT, a domain-specific LLM fine-tuned on Mistral-7B-Instruct-v0.2 using 107 curated requirements lists. ReqGPT employs a standardized prompt to generate high-quality documents and demonstrated superior performance over GPT-4 and Mistral in multiple criteria based on ISO 29148. Our results underscore ReqGPT's efficiency, accuracy, cost-effectiveness, and alignment with industry standards, making it an ideal choice for localized use and safeguarding data privacy in technical product development.
KW - fine-tuning
KW - large language models
KW - machine learning
KW - new product development
KW - requirements
KW - Engineering
UR - http://www.scopus.com/inward/record.url?scp=105022796500&partnerID=8YFLogxK
U2 - 10.1017/pds.2025.10288
DO - 10.1017/pds.2025.10288
M3 - Conference article in journal
AN - SCOPUS:105022796500
VL - 5
SP - 2741
EP - 2750
JO - Proceedings of the Design Society
JF - Proceedings of the Design Society
SN - 2732-527X
Y2 - 11 August 2025 through 14 August 2025
ER -