Related papers: Safurai-Csharp: Harnessing Synthetic Data to impro…

In recent years, developing compact and efficient large language models (LLMs) has emerged as a thriving area of research. Traditional Supervised Fine-Tuning (SFT), which relies on singular ground truth labels, often fails to capture…

High-quality instruction-tuning data is crucial for developing Large Language Models (LLMs) that can effectively navigate real-world tasks and follow human instructions. While synthetic data generation offers a scalable approach for…

Researchers have successfully applied large language models (LLMs) such as ChatGPT to reranking in an information retrieval context, but to date, such work has mostly been built on proprietary models hidden behind opaque API endpoints. This…

Code reviews are an integral part of software development and have been recognized as a crucial practice for minimizing bugs and favouring higher code quality. They serve as an important checkpoint before committing code and play an…

The advances of deep learning (DL) have paved the way for automatic software vulnerability repair approaches, which effectively learn the mapping from the vulnerable code to the fixed code. Nevertheless, existing DL-based vulnerability…

The increasing reliance on Large Language Models (LLMs) across diverse sectors highlights the need for robust domain-specific and language-specific evaluation datasets; however, the collection of such datasets is challenging due to privacy…

This paper presents a systematic investigation into the constrained generation capabilities of large language models (LLMs) in producing Songci, a classical Chinese poetry form characterized by strict structural, tonal, and rhyme…

With the recent unprecedented advancements in Artificial Intelligence (AI) computing, progress in Large Language Models (LLMs) is accelerating rapidly, presenting challenges in establishing clear guidelines, particularly in the field of…

Automating the decision of whether a code change requires manual review is vital for maintaining software quality in modern development workflows. However, the emergence of new programming languages and frameworks creates a critical…

Code completion, a highly valuable topic in the software development domain, has been increasingly promoted for use by recent advances in large language models (LLMs). To date, visible LLM-based code completion frameworks such as GitHub…

Large language models (LLMs) achieve strong performance across diverse tasks, largely driven by high-quality web data used in pre-training. However, recent studies indicate this data source is rapidly depleting. Synthetic data emerges as a…

Evaluating the programming robustness of large language models (LLMs) is paramount for ensuring their reliability in AI-based software development. However, adversarial attacks exhibit fundamental limitations that compromise fair robustness…

With the growing demand for deploying large language models (LLMs) across diverse applications, improving their inference efficiency is crucial for sustainable and democratized access. However, retraining LLMs to meet new user-specific…

Recently, both closed-source LLMs and open-source communities have made significant strides, outperforming humans in various general domains. However, their performance in specific professional domains such as medicine, especially within…

Automating code documentation through explanatory text can prove highly beneficial in code understanding. Large Language Models (LLMs) have made remarkable strides in Natural Language Processing, especially within software engineering tasks…

Code often suffers from performance bugs. These bugs necessitate the research and practice of code optimization. Traditional rule-based methods rely on manually designing and maintaining rules for specific performance bugs (e.g., redundant…

Optimal hyperparameter selection is critical for maximizing the performance of neural networks in computer vision, particularly as architectures become more complex. This work explores the use of large language models (LLMs) for…

Prior work has shown that finetuning large language models (LLMs) using machine-generated instruction-following data enables such models to achieve remarkable zero-shot capabilities on new tasks, and no human-written instructions are…

Manually annotating instruction data for large language models is difficult, costly, and hard to scale. Meanwhile, current automatic annotation methods typically rely on distilling synthetic data from proprietary LLMs, which not only limits…

Instruction fine-tuning is crucial for today's large language models (LLMs) to learn to follow instructions and align with human preferences. Conventionally, supervised data, including the instruction and the correct response, is required…