Related papers: ENCORE: Ensemble Learning using Convolution Neural…

Sequence-to-sequence models have been used to transform erroneous programs into correct ones when trained with a large enough dataset. Some recent studies also demonstrated strong empirical evidence that code review could improve the…

The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semantic bugs such as security vulnerabilities has proven…

Neural machine translation (NMT) architectures have achieved promising results for automatic program repair. Yet, they have the limitation of generating low-quality patches (e.g., not compilable patches). This is because the existing works…

Recent advances in leveraging LLMs for APR have demonstrated impressive capabilities in fixing software defects. However, current LLM-based approaches predominantly focus on mainstream programming languages like Java and Python, neglecting…

Back-translation (BT) is an effective semi-supervised learning framework in neural machine translation (NMT). A pre-trained NMT model translates monolingual sentences and makes synthetic bilingual sentence pairs for the training of the…

Research shows that errors in natural language can be corrected by translating texts to another language and back using language models. We explore to what extent this latent correction capability extends to Automated Program Repair (APR)…

This study explores the potential of Large Language Models (LLMs) in automating the repair of C programs. We present a framework that integrates spectrum-based fault localization (SBFL), runtime feedback, and Chain-of-Thought-structured…

Significant interest in applying Deep Neural Network (DNN) has fueled the need to support engineering of software that uses DNNs. Repairing software that uses DNNs is one such unmistakable SE need where automated tools could be beneficial;…

Phrase-based statistical machine translation (SMT) systems have previously been used for the task of grammatical error correction (GEC) to achieve state-of-the-art accuracy. The superiority of SMT systems comes from their ability to learn…

Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource…

The existing deep learning (DL)-based automated program repair (APR) models are limited in fixing general software defects. % We present {\tool}, a DL-based approach that supports fixing for the general bugs that require dependent changes…

Recent years have seen the rise of Deep Learning (DL) techniques applied to source code. Researchers have exploited DL to automate several development and maintenance tasks, such as writing commit messages, generating comments and detecting…

Neural Machine Translation (NMT) systems are known to degrade when confronted with noisy data, especially when the system is trained only on clean data. In this paper, we show that augmenting training data with sentences containing…

Evaluation in machine learning is usually informed by past choices, for example which datasets or metrics to use. This standardization enables the comparison on equal footing using leaderboards, but the evaluation choices become sub-optimal…

Grammar error correction (GEC) is an important application aspect of natural language processing techniques. The past decade has witnessed significant progress achieved in GEC for the sake of increasing popularity of machine learning and…

Automated program repair (APR) aims to fix software bugs without human intervention and template-based APR has been widely investigated with promising results. However, it is challenging for template-based APR to select the appropriate…

Thanks to the state-of-the-art Large Language Models (LLMs), language generation has reached outstanding levels. These models are capable of generating high quality content, thus making it a challenging task to detect generated text from…

Large language models (LLMs) have shown impressive effectiveness in various software engineering tasks, including automated program repair (APR). In this study, we take a deep dive into automated bug fixing utilizing LLMs. In contrast to…

GPT-2 and BERT demonstrate the effectiveness of using pre-trained language models (LMs) on various natural language processing tasks. However, LM fine-tuning often suffers from catastrophic forgetting when applied to resource-rich tasks. In…

Software development life cycle is profoundly influenced by bugs: their introduction, identification, and eventual resolution account for a significant portion of software cost. This has motivated software engineering researchers and…