TY - GEN
T1 - Utilizing Process Models in the Requirements Engineering Process Through Model2Text Transformation
AU - Klievtsova, Nataliia
AU - Mangler, Juergen
AU - Kampik, Timotheus
AU - Rinderle-Ma, Stefanie
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - With the advent of large language models (LLMs), requirements engineers have gained a powerful natural language processing tool to analyze, query, and validate a wide variety of textual artifacts, thus potentially supporting the whole re-quirements engineering process from requirements elicitation to management. However, the input for the requirements engineering process often encompasses a variety of potential information sources in various formats, especially graphical models such as process models. Hence, this work aims to contribute to the state of the art by assessing the feasibility of utilizing graphical process models and their textual representations in the requirements engineering process. In particular, we focus on the extraction of textual process descriptions from process models as i) input for the requirements engineering process and ii) documentation as the result of process-oriented requirements engineering. To this end, we explore, quantify, and compare traditional deterministic and LLM-based extraction methods where the latter includes GPT3, GPT3.5, GPT4, and LLAMA. The evaluation assesses output quality and information loss based on one data set. The results indicate that LLMs produce human-like process descriptions based on the predefined patterns, but apparently lack true comprehension of the process models.
AB - With the advent of large language models (LLMs), requirements engineers have gained a powerful natural language processing tool to analyze, query, and validate a wide variety of textual artifacts, thus potentially supporting the whole re-quirements engineering process from requirements elicitation to management. However, the input for the requirements engineering process often encompasses a variety of potential information sources in various formats, especially graphical models such as process models. Hence, this work aims to contribute to the state of the art by assessing the feasibility of utilizing graphical process models and their textual representations in the requirements engineering process. In particular, we focus on the extraction of textual process descriptions from process models as i) input for the requirements engineering process and ii) documentation as the result of process-oriented requirements engineering. To this end, we explore, quantify, and compare traditional deterministic and LLM-based extraction methods where the latter includes GPT3, GPT3.5, GPT4, and LLAMA. The evaluation assesses output quality and information loss based on one data set. The results indicate that LLMs produce human-like process descriptions based on the predefined patterns, but apparently lack true comprehension of the process models.
KW - AI4RE
KW - Large Language Models
KW - Process Descriptions
KW - Process Models
UR - http://www.scopus.com/inward/record.url?scp=85202725174&partnerID=8YFLogxK
U2 - 10.1109/RE59067.2024.00028
DO - 10.1109/RE59067.2024.00028
M3 - Conference contribution
AN - SCOPUS:85202725174
T3 - Proceedings of the IEEE International Conference on Requirements Engineering
SP - 205
EP - 217
BT - Proceedings - 32nd IEEE International Requirements Engineering Conference, RE 2024
A2 - Liebel, Grischa
A2 - Hadar, Irit
A2 - Spoletini, Paola
PB - IEEE Computer Society
T2 - 32nd IEEE International Requirements Engineering Conference, RE 2024
Y2 - 24 June 2024 through 28 June 2024
ER -