GPT-Powered Elicitation Interview Script Generator for Requirements Engineering Training

TL;DR

The paper tackles the scarcity of practical training materials for requirements elicitation interviews by introducing a GPT-powered script generator that uses a domain-specific knowledge base and prompt chaining to produce long, realistic interview scripts. It combines retrieval-like knowledge injection with an outline-based generation strategy to overcome token-length limitations and to maintain coherence across sections. Evaluation comprises automated GRUEN-based linguistic quality metrics and an expert judgment study across four domain scenarios, showing generally high naturalness and coherence, with identified gaps in completeness and depth on non-functional requirements. The work offers scalable, educational content for requirements engineering training and lays out a plan to broaden evaluation, diversify prompts and knowledge sources, and develop persona-based, multi-LLM interactions for richer training experiences.

Abstract

Elicitation interviews are the most common requirements elicitation technique, and proficiency in conducting these interviews is crucial for requirements elicitation. Traditional training methods, typically limited to textbook learning, may not sufficiently address the practical complexities of interviewing techniques. Practical training with various interview scenarios is important for understanding how to apply theoretical knowledge in real-world contexts. However, there is a shortage of educational interview material, as creating interview scripts requires both technical expertise and creativity. To address this issue, we develop a specialized GPT agent for auto-generating interview scripts. The GPT agent is equipped with a dedicated knowledge base tailored to the guidelines and best practices of requirements elicitation interview procedures. We employ a prompt chaining approach to mitigate the output length constraint of GPT to be able to generate thorough and detailed interview scripts. This involves dividing the interview into sections and crafting distinct prompts for each, allowing for the generation of complete content for each section. The generated scripts are assessed through standard natural language generation evaluation metrics and an expert judgment study, confirming their applicability in requirements engineering training.

Figures (2)

• Figure 1: Configuring custom GPT.
• Figure 2: Outline-based interview generation with custom GPT.