相关论文: Out of style: Misadventures with LLMs and code sty…

With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing…

Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. This work studies to what extent Large Language Models (LLMs) can…

With the rapid development of Large Language Models (LLMs), a large number of machine learning models have been developed to assist programming tasks including the generation of program code from natural language input. However, how to…

Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this…

Context: A substantial amount of work has been done to detect smells in source code using metrics-based and heuristics-based methods. Machine learning methods have been recently applied to detect source code smells; however, the current…

In the digital age, ensuring the correctness, safety, and reliability of software through formal verification is paramount, particularly as software increasingly underpins critical infrastructure. Formal verification, split into theorem…

Tools for rewriting, refactoring and optimizing code should be fast and correct. Large language models (LLMs), by their nature, possess neither of these qualities. Yet, there remains tremendous opportunity in using LLMs to improve code. We…

We present a general framework for unsupervised text style transfer with deep generative models. The framework models each sentence-label pair in the non-parallel corpus as partially observed from a complete quadruplet which additionally…

Developing automated and smart software vulnerability detection models has been receiving great attention from both research and development communities. One of the biggest challenges in this area is the lack of code samples for all…

Large language models (LLMs) for code are increasingly used in software development, but they remain static after pretraining while APIs and software libraries continue to evolve. Model editing offers a lightweight alternative to retraining…

As large language models (LLMs) excel at code reasoning, a natural question arises: can an LLM execute programs (i.e., act as an interpreter) purely based on a programming language's formal semantics? If so, it will enable rapid prototyping…

Text style transfer task requires the model to transfer a sentence of one style to another style while retaining its original content meaning, which is a challenging problem that has long suffered from the shortage of parallel data. In this…

Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly regarding the frequent updates of third-party library APIs.…

Code completion has become a central task, gaining significant attention with the rise of large language model (LLM)-based tools in software engineering. Although recent advances have greatly improved LLMs' code completion abilities,…

Modern LLMs struggle with efficient updates, as each new pretrained model version requires repeating expensive alignment processes. This challenge also applies to domain- or languagespecific models, where fine-tuning on specialized data…

The curse of knowledge can impede communication between experts and laymen. We propose a new task of expertise style transfer and contribute a manually annotated dataset with the goal of alleviating such cognitive biases. Solving this task…

Pre-trained language models have demonstrated impressive performance in both natural language processing and program understanding, which represent the input as a token sequence without explicitly modeling its structure. Some prior works…

Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences, which can be used to improve performance of many downstream NLP tasks. In this work, we propose a semi-supervised formality…

Modern software systems require code that is not only functional but also maintainable and well-structured. Although Large Language Models (LLMs) are increasingly used to automate software development, most studies focus on isolated,…

Text Style Transfer (TST) is performable through approaches such as latent space disentanglement, cycle-consistency losses, prototype editing etc. The prototype editing approach, which is known to be quite successful in TST, involves two…