LLMs for Uncertainty Identification in Self-Adaptive Robotics

This repository contains supplementary materials as part of the following paper.

📝 Paper Reference

Hassan Sartaj, Jalil Boudjadar, Mirgita Frasheri, Shaukat Ali, and Peter Gorm Larsen. "Identifying Uncertainty in Self-Adaptive Robotics with Large Language Models." IEEE Software, vol. 43, no. 1, pp. 89-97, Jan.-Feb. 2026, doi: 10.1109/MS.2025.3620578.
Publication Link

📂 Repository Contents

1. Prompt (LLMsPrompt.pdf) File

• A role-based prompt designed to identify uncertainties in self-adaptive robotics using large language models (LLMs).
• Includes:
  • Step-by-step instructions for LLMs.
  • An uncertainty questionnaire covering key uncertainty factors across the robotics software engineering lifecycle.

2. Findings and Analysis (Appendix-Additional-Results.pdf) File

• Results from additional analyses, including:
  • Cohen’s Kappa (K): Used to assess inter-rater reliability of the results.
  • Non-parametric Confidence Intervals: Calculated using the Bootstrap method for more statistical insights.

---