collaborators

8 papers

cs.SE2026

Graph Construction and Matching for Imperative Programs using Neural and Structural Methods

Arshad Beg, Diarmuid O'Donoghue, Rosemary Monahan

Reusing verification artefacts requires identifying structural and semantic similarities across programs and their specifications. In this paper, we focus on graph construction as…

cs.SE2026

Learning-Infused Formal Reasoning: From Contract Synthesis to Artifact Reuse and Formal Semantics

Arshad Beg, Diarmuid O'Donoghue, Rosemary Monahan

This paper articulates a long-term research vision for formal methods at the intersection with artificial intelligence, outlining multiple conceptual and technical dimensions and r…

cs.SE2026

Short Version of VERIFAI2026 Paper -- Learning Infused Formal Reasoning: Contract Synthesis, Artefact Reuse and Semantic Foundations

Arshad Beg, Diarmuid O'Donoghue, Rosemary Monahan

Artificial intelligence systems have achieved remarkable capability in natural language processing, perception and decision-making tasks. However, their behaviour often remains opa…

cs.SE2026

Evaluating LLM-Generated ACSL Annotations for Formal Verification

Arshad Beg, Diarmuid O'Donoghue, Rosemary Monahan

Formal specifications are crucial for building verifiable and dependable software systems, yet generating accurate and verifiable specifications for real-world C programs remains c…

cs.SE2025

Leveraging LLMs for Formal Software Requirements -- Challenges and Prospects

Arshad Beg, Diarmuid O'Donoghue, Rosemary Monahan

Software correctness is ensured mathematically through formal verification, which involves the resources of generating formal requirement specifications and having an implementatio…

cs.SE2025

Working Document -- Formalising Software Requirements with Large Language Models

Arshad Beg, Diarmuid O'Donoghue, Rosemary Monahan

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…