TY - CHAP

T1 - PROMPT ENGINEERING FOR REQUIREMENTS ELICITATION

T2 - ASME 2025 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC-CIE 2025

AU - Schiller, Kata Amanda

AU - Seibel, Arthur

N1 - Publisher Copyright: Copyright © 2025 by ASME.

PY - 2025

Y1 - 2025

N2 - Large language models (LLMs) offer new opportunities for automating requirements elicitation in early-stage product development. However, many existing approaches rely on complex architectures or fine-tuning, which are resource-intensive and often inaccessible to non-experts. This reveals a critical gap: the demand for lightweight, broadly applicable methods that support effective requirements generation without the need for specialized model training. Prompt engineering addresses this gap by guiding pre-trained LLMs through carefully crafted input instructions, thereby avoiding the need for additional training. This study evaluates eight prompt engineering techniques for generating requirements documents using OpenAI’s o1 model on the example of a smart electronic product. The analysis focuses on the structure of requirements lists and examines various methods, ranging from basic approaches (zero-shot, one-shot, and few-shot prompting), to reasoning-based techniques (chain-of-thought and tree-of-thought prompting), and advanced strategies (self-consistency, ensemble refinement, and choice shuffle ensemble). The outputs are assessed based on multiple categories using three LLMs, namely Llama-3.2-3B-Instruct, DeepSeek-R1-Distill-Qwen-7BGGUF, and Mistral-7B-Instruct-v0.3. The results show substantial variation in performance. Simpler prompts often produce incomplete or inconsistent outputs, while more advanced strategies show higher quality and coherence. In particular, combining few-shot prompting with tree-of-thought prompting and ensemble refinement produces the most reliable and well-structured requirements lists. These techniques enable the model to reason more transparently and iteratively refine its outputs. However, challenges remain such as susceptibility to hallucinations and a strong dependence on prompt design.

AB - Large language models (LLMs) offer new opportunities for automating requirements elicitation in early-stage product development. However, many existing approaches rely on complex architectures or fine-tuning, which are resource-intensive and often inaccessible to non-experts. This reveals a critical gap: the demand for lightweight, broadly applicable methods that support effective requirements generation without the need for specialized model training. Prompt engineering addresses this gap by guiding pre-trained LLMs through carefully crafted input instructions, thereby avoiding the need for additional training. This study evaluates eight prompt engineering techniques for generating requirements documents using OpenAI’s o1 model on the example of a smart electronic product. The analysis focuses on the structure of requirements lists and examines various methods, ranging from basic approaches (zero-shot, one-shot, and few-shot prompting), to reasoning-based techniques (chain-of-thought and tree-of-thought prompting), and advanced strategies (self-consistency, ensemble refinement, and choice shuffle ensemble). The outputs are assessed based on multiple categories using three LLMs, namely Llama-3.2-3B-Instruct, DeepSeek-R1-Distill-Qwen-7BGGUF, and Mistral-7B-Instruct-v0.3. The results show substantial variation in performance. Simpler prompts often produce incomplete or inconsistent outputs, while more advanced strategies show higher quality and coherence. In particular, combining few-shot prompting with tree-of-thought prompting and ensemble refinement produces the most reliable and well-structured requirements lists. These techniques enable the model to reason more transparently and iteratively refine its outputs. However, challenges remain such as susceptibility to hallucinations and a strong dependence on prompt design.

KW - Large Language Models

KW - Product Development

KW - Prompt Engineering

KW - Requirements Elicitation

KW - Engineering

UR - http://www.scopus.com/inward/record.url?scp=105024317303&partnerID=8YFLogxK

U2 - 10.1115/DETC2025-169451

DO - 10.1115/DETC2025-169451

M3 - Article in conference proceedings

AN - SCOPUS:105024317303

SN - 978-0-7918-8923-7

T3 - Proceedings of the ASME Design Engineering Technical Conference

BT - 51st Design Automation Conference (DAC)

A2 - Hao, Guang

A2 - Gan, Dongming

A2 - Plecnik, Mark

A2 - Huang, Bingling

PB - The American Society of Mechanical Engineers(ASME)

Y2 - 17 August 2025 through 20 August 2025

ER -