相关论文: Syntax Is Not Enough: An Empirical Study of Small …

Deploying small language models (7-9B parameters) as autonomous agents requires trust in their reasoning, not just their outputs. We reveal a critical reliability crisis: 50-69\% of correct answers from these models contain fundamentally…

Code completion is a prominent application of Large Language Models (LLMs) in software engineering. Due to the near real-time response requirements of this task, base models with small to medium-sized parameters are typically employed,…

Large Language Models (LLMs) promise to streamline software code reviews, but their ability to produce consistent assessments remains an open question. In this study, we tested four leading LLMs -- GPT-4o mini, GPT-4o, Claude 3.5 Sonnet,…

Automated tests play an important role in software evolution because they can rapidly detect faults introduced during changes. In practice, code-coverage metrics are often used as criteria to evaluate the effectiveness of test suites with…

Refactoring tools in popular Integrated Development Environments (IDEs) can introduce unintended behavioral changes or compilation errors, a persistent challenge that undermines developer trust in automated transformations. Traditional…

Neural language models (LMs) have been proved to significantly outperform classical n-gram LMs for language modeling due to their superior abilities to model long-range dependencies in text and handle data sparsity problems. And recently,…

Automated Code Revision (ACR) tools aim to reduce manual effort by automatically generating code revisions based on reviewer feedback. While ACR tools have shown promising performance on historical data, their real-world utility depends on…

Neural networks have in recent years shown promise for helping software engineers write programs and even formally verify them. While semantic information plays a crucial part in these processes, it remains unclear to what degree popular…

Large language models (LLMs) have achieved decent results on automated program repair (APR). However, the next token prediction training objective of decoder-only LLMs (e.g., GPT-4) is misaligned with the masked span prediction objective of…

Large Language Models (LLMs) have demonstrated remarkable capabilities in software engineering, yet comprehensive benchmarks covering diverse SE activities remain limited. We present a multi-task evaluation of 11 state-of-the-art LLMs…

Deployed language models must produce outputs that are both correct and format-compliant. We study this structured-output reliability gap using two mathematical benchmarks -- GSM8K and MATH -- as a controlled testbed: ground truth is…

Neural machine translation systems typically are trained on curated corpora and break when faced with non-standard orthography or punctuation. Resilience to spelling mistakes and typos, however, is crucial as machine translation systems are…

Code analysis is fundamental in Software Engineering, supporting debugging, optimization, and security assessment. Human developers approach it through syntax parsing, static semantics inference, and dynamic reasoning. Traditional tools are…

Many Transformer-based pre-trained models for code have been developed and applied to code-related tasks. In this paper, we review the existing literature, examine the suitability of model architectures for different tasks, and look at the…

In this study, we assess the efficacy of employing the ChatGPT language model to generate solutions for coding exercises within an undergraduate Java programming course. ChatGPT, a large-scale, deep learning-driven natural language…

High-quality computer science education is limited by the difficulty of providing instructor feedback to students at scale. While this feedback could in principle be automated, supervised approaches to predicting the correct feedback are…

This tool demonstration presents a research toolkit for a language model of Java source code. The target audience includes researchers studying problems at the granularity level of subroutines, statements, or variables in Java. In contrast…

Small-scale models offer various computational advantages, and yet to which extent size is critical for problem-solving abilities remains an open question. Specifically for solving grade school math, the smallest model size so far required…

Automatic program repair papers tend to repeatedly use the same benchmarks. This poses a threat to the external validity of the findings of the program repair research community. In this paper, we perform an empirical study of automatic…

Deep learning (DL) techniques are gaining more and more attention in the software engineering community. They have been used to support several code-related tasks, such as automatic bug fixing and code comments generation. Recent studies in…