English
Related papers

Related papers: Syntax Is Not Enough: An Empirical Study of Small …

200 papers

Formal specifications are essential for ensuring software correctness, yet manually writing them is tedious and error-prone. Large Language Models (LLMs) have shown promise in generating such specifications from natural language intents,…

Software Engineering · Computer Science 2025-07-15 Gehao Zhang , Zhenting Wang , Juan Zhai

Many techniques for automated program repair involve syntactic program transformations. Applying combinations of such transformations on faulty code yields fix candidates whose correctness must be determined. Exploring these combinations…

Providing effective feedback is important for student learning in programming problem-solving. In this sense, Large Language Models (LLMs) have emerged as potential tools to automate feedback generation. However, their reliability and…

Software Engineering · Computer Science 2025-03-20 Priscylla Silva , Evandro Costa

Automated Program Repair (APR) has evolved significantly with the advent of Large Language Models (LLMs). Fine-tuning LLMs for program repair is a recent avenue of research, with many dimensions which have not been explored. Existing work…

Software Engineering · Computer Science 2025-09-08 André Silva , Sen Fang , Martin Monperrus

Automated program repair techniques, which target to generating correct patches for real world defects automatically, have gained a lot of attention in the last decade. Many different techniques and tools have been proposed and developed.…

Software Engineering · Computer Science 2017-05-15 Jiajun Jiang , Yingfei Xiong

Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs), where LLMs refine their solutions using self-generated critiques that pinpoint the errors. This work explores whether…

Computation and Language · Computer Science 2024-06-07 Yunxiang Zhang , Muhammad Khalifa , Lajanugen Logeswaran , Jaekyeom Kim , Moontae Lee , Honglak Lee , Lu Wang

Automatic Program translation has enormous application value and hence has been attracting significant interest from AI researchers. However, we observe that current program translation models still make elementary syntax errors,…

Software Engineering · Computer Science 2023-10-24 Mengnan Qi , Yufan Huang , Maoquan Wang , Yongqiang Yao , Zihan Liu , Bin Gu , Colin Clement , Neel Sundaresan

Recent studies have adopted pre-trained language models, such as CodeT5 and CodeGPT, for automated program generation tasks like code generation, repair, and translation. Numerous language model-based approaches have been proposed and…

Software Engineering · Computer Science 2024-01-09 Yue Liu , Chakkrit Tantithamthavorn , Yonghui Liu , Li Li

Large language models such as Codex, have shown the capability to produce code for many programming tasks. However, the success rate of existing models is low, especially for complex programming tasks. One of the reasons is that language…

Software Engineering · Computer Science 2023-01-03 Zhiyu Fan , Xiang Gao , Martin Mirchev , Abhik Roychoudhury , Shin Hwei Tan

Defects4J is a large, peer-reviewed, structured dataset of real-world Java bugs. Each bug in Defects4J is provided with a test suite and at least one failing test case that triggers the bug. In this paper, we report on an experiment to…

Software Engineering · Computer Science 2015-12-24 Matias Martinez , Thomas Durieux , Jifeng Xuan , Romain Sommerard , Martin Monperrus

Popular IDEs frequently contain bugs in their refactoring implementations. Ensuring that a transformation preserves a program's behavior is a complex task. Traditional detection methods rely on predefined preconditions for each refactoring…

Software Engineering · Computer Science 2025-03-31 Rohit Gheyi , Marcio Ribeiro , Jonhnanthan Oliveira

As pre-trained models automate many code intelligence tasks, a widely used paradigm is to fine-tune a model on the task dataset for each programming language. A recent study reported that multilingual fine-tuning benefits a range of tasks…

Software Engineering · Computer Science 2023-03-29 Deze Wang , Boxing Chen , Shanshan Li , Wei Luo , Shaoliang Peng , Wei Dong , Xiangke Liao

Software vulnerabilities are now reported at an unprecedented speed due to the recent development of automated vulnerability hunting tools. However, fixing vulnerabilities still mainly depends on programmers' manual efforts. Developers need…

Cryptography and Security · Computer Science 2022-03-23 Jianlei Chi , Yu Qu , Ting Liu , Qinghua Zheng , Heng Yin

Security vulnerability repair is a difficult task that is in dire need of automation. Two groups of techniques have shown promise: (1) large code language models (LLMs) that have been pre-trained on source code for tasks such as code…

Software Engineering · Computer Science 2024-04-03 Yi Wu , Nan Jiang , Hung Viet Pham , Thibaud Lutellier , Jordan Davis , Lin Tan , Petr Babkin , Sameena Shah

Code completion is a popular software development tool integrated into all major IDEs. Many neural language models have achieved promising results in completion suggestion prediction on synthetic benchmarks. However, a recent study When…

Software Engineering · Computer Science 2020-11-10 Gareth Ari Aye , Seohyun Kim , Hongyu Li

The increasing prevalence of software bugs has made automated program repair (APR) a key research focus. Large language models (LLMs) offer new opportunities for APR, but existing studies mostly rely on smaller, earlier-generation models…

Software Engineering · Computer Science 2025-06-17 Jiajun Sun , Fengjie Li , Xinzhu Qi , Hongyu Zhang , Jiajun Jiang

Code completion is a key feature of Integrated Development Environments (IDEs), aimed at predicting the next tokens a developer is likely to write, helping them write code faster and with less effort. Modern code completion approaches are…

Software Engineering · Computer Science 2024-03-25 Matteo Ciniselli , Alberto Martin-Lopez , Gabriele Bavota

Human developers can produce code with cybersecurity bugs. Can emerging 'smart' code completion tools help repair those bugs? In this work, we examine the use of large language models (LLMs) for code (such as OpenAI's Codex and AI21's…

Cryptography and Security · Computer Science 2022-08-16 Hammond Pearce , Benjamin Tan , Baleegh Ahmad , Ramesh Karri , Brendan Dolan-Gavitt

We introduce NSEdit (neural-symbolic edit), a novel Transformer-based code repair method. Given only the source code that contains bugs, NSEdit predicts an editing sequence that can fix the bugs. The edit grammar is formulated as a regular…

Machine Learning · Computer Science 2022-04-19 Yaojie Hu , Xingjian Shi , Qiang Zhou , Lee Pike

Test-based automated program repair has been a prolific field of research in software engineering in the last decade. Many approaches have indeed been proposed, which leverage test suites as a weak, but affordable, approximation to program…