Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Human-AI Synergy in Requirements Engineering: A Framework and Preliminary Study

Mateen Ahmed Abbasi, Petri Ihantola, Tommi Mikkonen, Niko Mäkitalo

TL;DR

The paper addresses the inefficiencies and risks of traditional Requirements Engineering by proposing the Human-AI RE Synergy Model (HARE-SM), which embeds human oversight into AI-assisted elicitation, analysis, and validation. It outlines a four-phase roadmap (conceptual modeling, prototyping, model fine-tuning, and empirical evaluation) and introduces a functional prototype—the Acceptance Criteria Assistant—that compares outputs from multiple models and logs user interactions for auditability. The work foregrounds explainability, bias mitigation, and trust calibration as core design principles to enable responsible, in-the-loop AI augmentation of RE. If validated in real-world settings, HARE-SM promises scalable, transparent, and trustworthy AI-enabled RE across semi-structured and unstructured data in collaborative development environments.

Abstract

The future of Requirements Engineering (RE) is increasingly driven by artificial intelligence (AI), reshaping how we elicit, analyze, and validate requirements. Traditional RE is based on labor-intensive manual processes prone to errors and complexity. AI-powered approaches, specifically large language models (LLMs), natural language processing (NLP), and generative AI, offer transformative solutions and reduce inefficiencies. However, the use of AI in RE also brings challenges like algorithmic bias, lack of explainability, and ethical concerns related to automation. To address these issues, this study introduces the Human-AI RE Synergy Model (HARE-SM), a conceptual framework that integrates AI-driven analysis with human oversight to improve requirements elicitation, analysis, and validation. The model emphasizes ethical AI use through transparency, explainability, and bias mitigation. We outline a multi-phase research methodology focused on preparing RE datasets, fine-tuning AI models, and designing collaborative human-AI workflows. This preliminary study presents the conceptual framework and early-stage prototype implementation, establishing a research agenda and practical design direction for applying intelligent data science techniques to semi-structured and unstructured RE data in collaborative environments.

Towards Human-AI Synergy in Requirements Engineering: A Framework and Preliminary Study

TL;DR

The paper addresses the inefficiencies and risks of traditional Requirements Engineering by proposing the Human-AI RE Synergy Model (HARE-SM), which embeds human oversight into AI-assisted elicitation, analysis, and validation. It outlines a four-phase roadmap (conceptual modeling, prototyping, model fine-tuning, and empirical evaluation) and introduces a functional prototype—the Acceptance Criteria Assistant—that compares outputs from multiple models and logs user interactions for auditability. The work foregrounds explainability, bias mitigation, and trust calibration as core design principles to enable responsible, in-the-loop AI augmentation of RE. If validated in real-world settings, HARE-SM promises scalable, transparent, and trustworthy AI-enabled RE across semi-structured and unstructured data in collaborative development environments.

Abstract

The future of Requirements Engineering (RE) is increasingly driven by artificial intelligence (AI), reshaping how we elicit, analyze, and validate requirements. Traditional RE is based on labor-intensive manual processes prone to errors and complexity. AI-powered approaches, specifically large language models (LLMs), natural language processing (NLP), and generative AI, offer transformative solutions and reduce inefficiencies. However, the use of AI in RE also brings challenges like algorithmic bias, lack of explainability, and ethical concerns related to automation. To address these issues, this study introduces the Human-AI RE Synergy Model (HARE-SM), a conceptual framework that integrates AI-driven analysis with human oversight to improve requirements elicitation, analysis, and validation. The model emphasizes ethical AI use through transparency, explainability, and bias mitigation. We outline a multi-phase research methodology focused on preparing RE datasets, fine-tuning AI models, and designing collaborative human-AI workflows. This preliminary study presents the conceptual framework and early-stage prototype implementation, establishing a research agenda and practical design direction for applying intelligent data science techniques to semi-structured and unstructured RE data in collaborative environments.

Paper Structure

This paper contains 15 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Motivation and Related Work
  3. Requirements Engineering (RE) and AI Integration
  4. Ethical Considerations & Bias
  5. Need for Human-AI Collaboration in RE
  6. Research Roadmap
  7. Research Questions
  8. Methodology
  9. Human-AI RE Synergy Model (HARE-SM)
  10. HARE-SM Prototype
  11. Prototype Features
  12. System Architecture
  13. Implementation and Model Support
  14. Future Work
  15. Conclusions

Figures (4)

  • Figure 1: Research phases introduced.
  • Figure 2: Human-AI RE Synergy Model (HARE-SM)
  • Figure 3: Annotated interface of the Human-in-the-Loop Acceptance Criteria Assistant. (A) Session Information (unique ID and device type). (B) User-story Input Field. (C) Model Selection Area. (D) Generate Button. (E) LLM Output Panels. (F) Feedback Controls. (G) Submit Feedback. (H) Download Feedback Log.
  • Figure 4: System architecture of the Acceptance Criteria Assistant prototype. (A) Prototype user interface for interactive acceptance criteria generation. (B) LLM API layer including tokenization and model servers. (C) Logging service using in-memory session state and optional Excel export for feedback capture. (D) Data export module generating CSV/XLSX logs for analysis.