Finished my Ph.D. in Computer Science at UCL, my research focuses on advancing automated…

• Precise Data-Driven Approximation for Program Analysis via Fuzzing

  2023 38th IEEE/ACM International Conference on Automated Software Engineering September 14, 2023

  Program analysis techniques such as abstract interpretation and symbolic execution suffer from imprecision due to over- and underapproximation, which results in false alarms and missed violations. To alleviate this imprecision, we propose a novel data structure, program state probability (PSP), that leverages execution samples to probabilistically approximate reachable program states.

  See publication

• Rete: Learning namespace representation for program repair

  2023 IEEE/ACM 45th International Conference on Software Engineering May 20, 2023

  A key challenge of automated program repair is finding correct patches in the vast search space of candidate patches. Real-world programs define large namespaces of variables that considerably contributes to the search space explosion. Existing program repair approaches neglect information about the program namespace, which makes them inefficient and increases the chance of test-overfitting. We propose Rete, a new program repair technique, that learns project-independent information about…

  A key challenge of automated program repair is finding correct patches in the vast search space of candidate patches. Real-world programs define large namespaces of variables that considerably contributes to the search space explosion. Existing program repair approaches neglect information about the program namespace, which makes them inefficient and increases the chance of test-overfitting. We propose Rete, a new program repair technique, that learns project-independent information about program namespace and uses it to navigate the search space of patches. Rete uses a pretrained RoBERTa model to extract project-independent information about variable CDU chains, defuse chains augmented with control flow.

  See publication

• Trident: Controlling side effects in automated program repair

  IEEE Transactions on Software Engineering December 1, 2021

  The goal of program repair is to eliminate a bug in a given program by automatically modifying its source code. The majority of real-world software is written in imperative programming languages. Each function or expression in imperative code may have side effects, observable effects beyond returning a value. Existing program repair approaches have a limited ability to handle side effects. Previous test-driven semantic repair approaches only synthesise patches without side effects. Heuristic…

  The goal of program repair is to eliminate a bug in a given program by automatically modifying its source code. The majority of real-world software is written in imperative programming languages. Each function or expression in imperative code may have side effects, observable effects beyond returning a value. Existing program repair approaches have a limited ability to handle side effects. Previous test-driven semantic repair approaches only synthesise patches without side effects. Heuristic repair approaches generate patches with side effects only if suitable code fragments exist in the program or a database of repair patterns, or can be derived from training data. This work introduces Trident, the first test-driven program repair approach that synthesizes patches with side effects without relying on the plastic surgery hypothesis, a database of patterns, or training data.

  See publication

• The Fact Selection Problem in LLM-Based Program Repair

  In Review

  Recent research has shown that incorporating bug-related facts, such as stack traces and GitHub issues, into prompts enhances the bug-fixing capabilities of large language models (LLMs). Considering the ever-increasing context window of these models, a critical question arises: what and how many facts should be included in prompts to maximise the chance of correctly fixing bugs? To answer this question, we conducted a large-scale study, employing over 19K prompts featuring various combinations…

  Recent research has shown that incorporating bug-related facts, such as stack traces and GitHub issues, into prompts enhances the bug-fixing capabilities of large language models (LLMs). Considering the ever-increasing context window of these models, a critical question arises: what and how many facts should be included in prompts to maximise the chance of correctly fixing bugs? To answer this question, we conducted a large-scale study, employing over 19K prompts featuring various combinations of seven diverse facts to rectify 314 bugs from open-source Python projects within the BugsInPy benchmark. Our findings revealed that each fact, ranging from simple syntactic details like code context to semantic information previously unexplored in the context of LLMs such as angelic values, is beneficial.

  See publication

• ACM SIGSOFT Distinguished Paper Award

  ACM

  May 2023

  Won ACM SIGSOFT Distinguished paper award at International Conference on Software Engineering for my paper on automated program repair.