Automated Formalization of Probabilistic Requirements from Structured Natural Language

2025-12-15

AI Summary

Probabilistic requirements in safety-critical systems are difficult to model and formalize accurately. Method: This paper proposes a structured natural language extension framework for probabilistic requirements—built upon NASA’s FRET—that enables developers to specify uncertain requirements in a human-readable, verifiable manner and automatically translates them into semantically faithful probabilistic temporal logic formulas (pCTL/pLTL). Contribution/Results: The framework introduces (i) a novel translation mechanism jointly enforcing syntactic and semantic correctness; (ii) Coq-assisted formal semantics modeling; and (iii) an end-to-end automated toolchain. Evaluated on an autonomous spacecraft decision-making case study, the approach achieves 100% syntactic correctness and semantic consistency in generated formulas, significantly improves analysis efficiency, and substantially reduces requirement modeling errors.

Technology Category

• Natural Language Processing: Safety and Robustness
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Data transparency and provenance

Abstract

Integrating autonomous and adaptive behavior into software-intensive systems presents significant challenges for software development, as uncertainties in the environment or decision-making processes must be explicitly captured. These challenges are amplified in safety- and mission-critical systems, which must undergo rigorous scrutiny during design and development. Key among these challenges is the difficulty of specifying requirements that use probabilistic constructs to capture the uncertainty affecting these systems. To enable formal analysis, such requirements must be expressed in precise mathematical notations such as probabilistic logics. However, expecting developers to write requirements directly in complex formalisms is unrealistic and highly error-prone. We extend the structured natural language used by NASA's Formal Requirement Elicitation Tool (FRET) with support for the specification of unambiguous and correct probabilistic requirements, and develop an automated approach for translating these requirements into logical formulas. We propose and develop a formal, compositional, and automated approach for translating structured natural-language requirements into formulas in probabilistic temporal logic. To increase trust in our formalizations, we provide assurance that the generated formulas are well-formed and conform to the intended semantics through an automated validation framework and a formal proof. The extended FRET tool enables developers to specify probabilistic requirements in structured natural language, and to automatically translate them into probabilistic temporal logic, making the formal analysis of autonomous and adaptive systems more practical and less error-prone.

Problem

• Automating translation of probabilistic requirements into formal logic
• Enabling formal analysis of autonomous systems via structured language
• Reducing errors in specifying probabilistic requirements for safety-critical systems

Innovation

• Extends structured natural language with probabilistic requirement support
• Automates translation to probabilistic temporal logic formulas
• Provides validation framework ensuring semantic correctness