相关论文: Neural Program Repair with Execution-based Backpro…

Large Language Models (LLMs) show promising performance on various programming tasks, including Automatic Program Repair (APR). However, most approaches to LLM-based APR are limited to the static analysis of the programs, while disregarding…

Recent studies have proven that the training of neural machine translation (NMT) can be facilitated by mimicking the learning process of humans. Nevertheless, achievements of such kind of curriculum learning rely on the quality of…

The brain processes information through many layers of neurons. This deep architecture is representationally powerful, but it complicates learning by making it hard to identify the responsible neurons when a mistake is made. In machine…

LLM-based automated program repair (APR) techniques have shown promising results in reducing debugging costs. However, prior results can be affected by data leakage: large language models (LLMs) may memorize bug fixes when evaluation…

Providing feedback on programming assignments is a tedious task for the instructor, and even impossible in large Massive Open Online Courses with thousands of students. Previous research has suggested that program repair techniques can be…

Large language models (LMs), while powerful, are not immune to mistakes, but can be difficult to retrain. Our goal is for an LM to continue to improve after deployment, without retraining, using feedback from the user. Our approach pairs an…

Many complex physical systems admit natural decomposition into an exactly solvable component and a perturbative correction. Rather than training neural networks to learn complete trajectories from scratch, we introduce Neural Network…

Non-autoregressive neural machine translation (NAT) predicts the entire target sequence simultaneously and significantly accelerates inference process. However, NAT discards the dependency information in a sentence, and thus inevitably…

Providing personalized and timely feedback for student's programming assignments is useful for programming education. Automated program repair (APR) techniques have been used to fix the bugs in programming assignments, where the Large…

Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between…

Existing template and learning-based APR tools have successfully found patches for many benchmark faults. However, our analysis of existing results shows that omission faults pose a significant challenge to these techniques. For template…

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that…

Automated Program Repair (APR) helps improve the efficiency of software development and maintenance. Recent APR techniques use deep learning, particularly the encoder-decoder architecture, to generate patches. Though existing DL-based APR…

Automated Program Repair (APR) aims to help developers automatically patch software bugs. However, current state-of-the-art traditional and learning-based APR techniques face the problem of limited patch variety, failing to fix complicated…

Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT frameworks, a behavior model generates multiple completions with…

To support software developers in finding and fixing software bugs, several automated program repair techniques have been introduced. Given a test suite, standard methods usually either synthesize a repair, or navigate a search space of…

Automated Program Repair (APR) is a vital area in software engineering aimed at generating automatic patches for vulnerable programs. While numerous techniques have been proposed for repairing classical programs, the realm of quantum…

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

We propose a path-based approach to program repair for imperative programs. Our repair framework takes as input a faulty program, a logic specification that is refuted, and a hint where the fault may be located. An iterative abstraction…

IR-based fault localization approaches achieves promising results when locating faulty files by comparing a bug report with source code. Unfortunately, they become less effective to locate faulty methods. We conduct a preliminary study to…