Explanipedia

Reducing Hallucinations in LLM-Generated Code via Semantic Triangulation Open

Haotian Xu, Sergey Mechtaev · 2025

When generating code from natural language prompts, an LLM samples programs from a probability distribution, many of which might be incorrect. Sample consensus techniques - such as majority voting or validation against generated tests or s…

Oracle-Guided Program Selection from Large Language Models Open

Zhiyu Fan, Haifeng Ruan, Sergey Mechtaev, Abhik Roychoudhury · 2024

F1X at APR-COMP 2024 Open

Sergey Mechtaev, Shin Hwei Tan · 2024

User-Centric Deployment of Automated Program Repair at Bloomberg Open

D. A. Williams, James P. Callan, Serkan Kırbaş, Sergey Mechtaev, Justyna Petke , et al. · 2024

Automated program repair (APR) tools have unlocked the potential for the rapid rectification of codebase issues. However, to encourage wider adoption of program repair in practice, it is necessary to address the usability concerns related …

The Fact Selection Problem in LLM-Based Program Repair Open

Nikhil Parasaram, Huijie Yan, Boyu Yang, Zineb Flahy, Abriele Qudsi , et al. · 2024

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 th…

Program Repair Guided by Datalog-Defined Static Analysis Open

Yu Liu, Sergey Mechtaev, Pavle Subotić, Abhik Roychoudhury · 2023

Automated program repair relying on static analysis complements test-driven repair, since it does not require failing tests to repair a bug, and it avoids test-overfitting by considering program properties. Due to the rich variety and comp…

User-Centric Deployment of Automated Program Repair at Bloomberg Open

David L. Williams, James P. Callan, Serkan Kırbaş, Sergey Mechtaev, Justyna Petke , et al. · 2023

Automated program repair (APR) tools have unlocked the potential for the rapid rectification of codebase issues. However, to encourage wider adoption of program repair in practice, it is necessary to address the usability concerns related …

International Workshop on Automated Program Repair APR 2023: Message from the APR 2023 Chairs Open

Shin Hwei Tan, Dongsun Kim, Sergey Mechtaev, Yuriy Brun · 2023

We extend a warm welcome to the third International Workshop on Automated Program Repair (APR 2023), held at ICSE 2023 in Melbourne, Australia. Since 2020, the APR workshop has been an annual fixture of the International Conference on Soft…

Fair decision making via automated repair of decision trees Open

Jiang Zhang, Ivan Beschastnikh, Sergey Mechtaev, Abhik Roychoudhury · 2022

Data-driven decision-making allows more resource allocation tasks to be done by programs. Unfortunately, real-life training datasets may capture human biases, and the learned models can be unfair. To resolve this, one could either train a …

Organizing Committee Open

Sergey Mechtaev, Shin Hwei Tan, Martin Monperrus, Lingming Zhang · 2021

rshariffdeen/CPR: Initial Release Open

Ridwan Shariffdeen, Yannic Noller, Sergey Mechtaev · 2021

The first official release for CPR. We added all parts of our tool and all evaluation subjects to support the reproduction of our results. This release is submitted to the PLDI 2021 Artifact Evaluation.

Fairness-guided SMT-based Rectification of Decision Trees and Random Forests Open

Jiang Zhang, Ivan Beschastnikh, Sergey Mechtaev, Abhik Roychoudhury · 2020

Data-driven decision making is gaining prominence with the popularity of various machine learning models. Unfortunately, real-life data used in machine learning training may capture human biases, and as a result the learned models may lead…

Crash-avoiding program repair Open

Xiang Gao, Sergey Mechtaev, Abhik Roychoudhury · 2019

Existing program repair systems modify a buggy program so that the modified program passes given tests. The repaired program may not satisfy even the most basic notion of correctness, namely crash-freedom. In other words, repair tools migh…

Test-Equivalence Analysis for Automatic Patch Generation Open

Sergey Mechtaev, Xiang Gao, Shin Hwei Tan, Abhik Roychoudhury · 2018

Automated program repair is a problem of finding a transformation (called a patch) of a given incorrect program that eliminates the observable failures. It has important applications such as providing debugging aids, automatically grading …

Partitioning Patches into Test-equivalence Classes for Scaling Program\n Repair Open

Sergey Mechtaev, Xiang Gao, Shin Hwei Tan, Abhik Roychoudhury · 2017

Automated program repair is a problem of finding a transformation (called a\npatch) of a given incorrect program that eliminates the observable failures. It\nhas important applications such as providing debugging aids, automatically\ngradi…

Partitioning Patches into Test-equivalence Classes for Scaling Program Repair Open

Sergey Mechtaev, Xiang Gao, Shin Hwei Tan, Abhik Roychoudhury · 2017

Automated program repair is a problem of finding a transformation (called a patch) of a given incorrect program that eliminates the observable failures. It has important applications such as providing debugging aids, automatically grading …

Sergey Mechtaev YOU? Author Swipe