5 papers
Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability
Pedro Orvalho, Marta Kwiatkowska, Guillem Alenyà +1
Large Language Models (LLMs) excel at understanding natural language but struggle with optimisation tasks involving multiple constraints and user-defined preferences, which commonl…
Exact Verification of Graph Neural Networks with Incremental Constraint Solving
Minghao Liu, Chia-Hsuan Lu, Marta Kwiatkowska
Graph neural networks (GNNs) are increasingly often employed in high-stakes applications, such as fraud detection or healthcare, but are susceptible to adversarial attacks. A numbe…
Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?
Pedro Orvalho, Marta Kwiatkowska
With the widespread adoption of vibe coding, understanding the reasoning and robustness of Large Language Models (LLMs) is critical for their reliable use in programming tasks. Whi…
Model-Based Diagnosis with Multiple Observations: A Unified Approach for C Software and Boolean Circuits
Pedro Orvalho, Marta Kwiatkowska, Mikoláš Janota +1
Debugging is one of the most time-consuming and expensive tasks in software development and circuit design. Several formula-based fault localisation (FBFL) methods have been propos…
PyVeritas: On Verifying Python via LLM-Based Transpilation and Bounded Model Checking for C
Pedro Orvalho, Marta Kwiatkowska
Python has become the dominant language for general-purpose programming, yet it lacks robust tools for formal verification. In contrast, programmers working in languages such as C…