From Brittle LLM Code Reasoning to MaxSAT-Based Verified Repairs @ UCL
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 …
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 …
This paper introduces MENTOR, a semantic automated program repair (APR) framework designed to fix faulty student programs. MENTOR validates repairs through execution on a test …
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 …
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 …
This paper introduces a novel fault localization approach for C programs with multiple faults. CFaults leverages Model-Based Diagnosis (MBD) with multiple observations and …