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 neuro-symbolic approach that combines Vision-Language Models (VLMs) with MaxSAT reasoning to improve reliability on structured visual reasoning …
In this talk, we will present ProHelp, an automated assessment platform for Prolog built on top of GitSEED, and evaluate it in a large undergraduate logic programming course with …
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 …
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 …
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 talk, I will present my PhD work on MENTOR, a semantic automated program repair framework designed to provide meaningful feedback for introductory programming assignments.
In this talk, I will present approaches that leverage the precision of formal logic and the adaptability of learning-based models to enable intelligent code generation, automated …
In this talk I will present a hybrid method to automated repair of C code, using Maximum Satisfiability (MaxSAT)-based fault localization, CFaults, to localize bugs and LLMs to …
In this talk, I will present our evaluation on whether state-of-the-art LLMs with up to 8B parameters can reason about Python programs or are simply guessing.
In my talk, I will present MENTOR, a semantic automated program repair (APR) framework designed to provide Automated Feedback for Introductory Programming Exercises.
Nesta palestra, irei apresentar o sistema MENTOR, uma ferramenta de reparação automática de programas orientada para fornecer feedback automatizado para exercícios introdutórios de …
In this talk I will present our novel approach that combines the strengths of both FM-based fault localization and LLMs, via zero-shot learning, to enhance Automated Program …
In this talk I will present GitSEED, a language-agnostic automated assessment tool designed for Programming Education and Software Engineering (SE) and backed by GitLab.
In this talk I will present a hybrid method to automated repair of C code, using Maximum Satisfiability (MaxSAT)-based fault localization, CFaults, to localize bugs and LLMs to …