← Back to Publications List

Operationalizing LLM Safety in Requirements Engineering: Writing and Validating Testable Safety Requirements

Students & Supervisors

Student Authors
Monika Hossain
Master of Science in Computer Science, FST
Robiul Islam
Master of Science in Computer Science, FST
Nousheen Jahan
Master of Science in Computer Science, FST
Supervisors
Prof. Dr. Kamruddin Nur
Professor, Faculty, FST
Rifat Al Mamun Rudro
Lecturer, Faculty, FST

Abstract

In response to the absence of standardized safety testing protocols for Large Language Models (LLMs), this study introduces a rigorous framework that operationalizes abstract safety guidelines into empirical testing requirements. By fine-tuning a DeBERTa-v3 model on the ToxiGen corpus utilizing cost-sensitive learning, the methodology effectively mitigates class-imbalance while optimizing for safety-critical recall. Evaluation of this proposed safety oracle yielded an accuracy of 86.68% and a precision of 91.09%, employing a highly conservative decision threshold (τ = 0.08) to aggressively identify toxic outputs. Ultimately, this approach establishes a reproducible regression testing paradigm that generates audit-ready documentation, thereby facilitating the secure deployment of LLMs in production environments.

Keywords

Requirements engineering LLM safety testable safety requirements toxic content detection safety evaluation large language models

Publication Details

  • Type of Publication:
  • Conference Name: 2026 International Conference on Frontiers of Engineering and Emerging Technologies
  • Date of Conference: 22/04/2026 - 22/04/2026
  • Venue: University of Bahrain, Kingdom of Bahrain
  • Organizer: University of Bahrain