CodeMind: A Framework to Challenge Large Language Models for Code Reasoning

1 code implementation • 15 Feb 2024 • Changshu Liu, Shizhuo Dylan Zhang, Ali Reza Ibrahimzada, Reyhaneh Jabbarvand

The first two evaluate models to predict the execution output of an arbitrary code or code the model could correctly synthesize.

White-box Compiler Fuzzing Empowered by Large Language Models

1 code implementation • 24 Oct 2023 • Chenyuan Yang, Yinlin Deng, Runyu Lu, Jiayi Yao, Jiawei Liu, Reyhaneh Jabbarvand, Lingming Zhang

Nonetheless, prompting LLMs with compiler source-code information remains a missing piece of research in compiler testing.

Code Generation Compiler Optimization

Automated Bug Generation in the era of Large Language Models

no code implementations • 3 Oct 2023 • Ali Reza Ibrahimzada, Yang Chen, Ryan Rong, Reyhaneh Jabbarvand

From the classic software engineering point of view, a hard-to-repair bug differs from the correct code in multiple locations, making it hard to localize and repair.

Program Repair

LeTI: Learning to Generate from Textual Interactions

1 code implementation • 17 May 2023 • Xingyao Wang, Hao Peng, Reyhaneh Jabbarvand, Heng Ji

We explore LMs' potential to learn from textual interactions (LETI) that not only check their correctness with binary labels but also pinpoint and explain errors in their outputs through textual feedback.

Code Generation Event Argument Extraction

Perfect is the enemy of test oracle

1 code implementation • 3 Feb 2023 • Ali Reza Ibrahimzada, Yigit Varli, Dilara Tekinoglu, Reyhaneh Jabbarvand

This paper presents SEER, a learning-based approach that in the absence of test assertions or other types of oracle, can determine whether a unit test passes or fails on a given method under test (MUT).