In this talk, we will present an empirical study investigating whether state-of-the-art Large Language Models (LLMs) can genuinely reason about Python programs or are simply …
In this talk, we will present a framework for solving MaxSAT problems expressed in natural language by combining large language models with the PySAT toolkit. We will show how LLMs …
Excited to share that two of our papers have been accepted at EPIA 2026, covering the robustness of LLMs for code understanding and neuro-symbolic feedback for Vision-Language …
In this paper we assess whether SOTA LLMs can reason about Python programs or are simply guessing. We apply five semantics-preserving code mutations, which maintain program …
Excited to share that three of our papers have been accepted at FLoC 2026, covering automated feedback for Prolog education, data-driven mutation testing for Prolog, and …
In this paper, we study a neuro-symbolic approach in which an LLM translates a natural language description of an optimisation problem into executable Python code using PySAT. The …
In this talk, we examine the limitations of Large Language Models (LLMs) in semantic code reasoning, showing that their predictions may change under semantics-preserving code …
LLMs for code often lack true semantic understanding, evidenced by their instability under semantics-preserving transformations, and we address this by integrating formal methods …
🔎🐛 Sherlock4Py 🐍 MaxSAT-Based Misbehaviour Verification and Localisation Framework for Python Sherlock4Py is a research project investigating how formal reasoning and Large …
In this talk I will present PyVeritas, a novel framework that leverages Large Language Models (LLMs) for high-level transpilation from Python to C, followed by bounded model …
In this paper, we propose PyVeritas, a novel framework that leverages Large Language Models (LLMs) for high-level transpilation from Python to C, followed by bounded model checking …
I’m excited to share that our paper on PyVeritas has been accepted to the P-AI-FM-26 Workshop @ AAAI 2026! 📄
Modern foundation models, including Large Language Models (LLMs) and Vision-Language Models (VLMs), have remarkable capabilities for understanding natural language, code, and …
This PhD thesis presents MENTOR, a semantic automated program repair (APR) framework designed to provide Automated Feedback for Introductory Programming Exercises.
In this paper, we propose a novel approach that combines the strengths of both FM-based fault localization and LLMs, via zero-shot learning, to enhance APR for IPAs. Our method …
Localising system faults has long been recognised as one of the most time-consuming and costly tasks in software engineering. Given a buggy system, fault localisation (FL) refers …