ACM Survey Draft on Formalising Software Requirements with Large Language Models

2025-06-17

AI Summary

Large language models (LLMs) are increasingly applied in software requirements formalization, yet their integration remains disconnected from foundational formal methods—particularly unified theories of programming (UTP) and institutional theory—limiting theoretical grounding and practical reliability. Method: This study systematically reviews 94 publications, combining bibliometric analysis, requirements traceability modeling, and rigorous LLM capability boundary assessment. It introduces a novel cross-paradigm mapping framework linking LLM capabilities to UTP and institutional theory, and proposes a dual-path evolutionary model contrasting lightweight heuristics with strict formal guarantees. Contribution/Results: We construct a structured knowledge graph that delineates LLMs’ applicability boundaries and core challenges in requirements consistency verification, specification generation, and formal transformation. The work establishes both a theoretical foundation and actionable guidelines for leveraging LLMs in trustworthy, formally grounded requirements engineering.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This draft is a working document, having a summary of nighty-four (94) papers with additional sections on Traceability of Software Requirements (Section 4), Formal Methods and Its Tools (Section 5), Unifying Theories of Programming (UTP) and Theory of Institutions (Section 6). Please refer to abstract of [7,8]. Key difference of this draft from our recently anticipated ones with similar titles, i.e. AACS 2025 [7] and SAIV 2025 [8] is: [7] is a two page submission to ADAPT Annual Conference, Ireland. Submitted on 18th of March, 2025, it went through the light-weight blind review and accepted for poster presentation. Conference was held on 15th of May, 2025. [8] is a nine page paper with additional nine pages of references and summary tables, submitted to Symposium on AI Verification (SAIV 2025) on 24th of April, 2025. It went through rigorous review process. The uploaded version on arXiv.org [8] is the improved one of the submission, after addressing the specific suggestions to improve the paper.

Problem

• Surveying formalization of software requirements using LLMs
• Exploring traceability in software requirements engineering
• Comparing formal methods and unifying programming theories

Innovation

• Formalizing requirements with Large Language Models
• Traceability in Software Requirements analysis
• Unifying Theories of Programming for verification