Related papers: Can Programming Languages Boost Each Other via Ins…
Underlying data distributions of natural language, programming code, and mathematical symbols vary vastly, presenting a complex challenge for large language models (LLMs) that strive to achieve high performance across all three domains…
Recent leaps in large language models (LLMs) caused a revolution in programming tools (like GitHub Copilot) that can help with code generation, debugging, and even performance optimization. In this paper, we focus on the capabilities of the…
Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM…
Most software maintenance and evolution tasks require developers to understand the source code of their software systems. Software developers usually inspect class comments to gain knowledge about program behavior, regardless of the…
Recent advancements in large language models (LLMs) have significantly enhanced code generation from natural language prompts. The HumanEval Benchmark, developed by OpenAI, remains the most widely used code generation benchmark. However,…
Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks. As most research mainly focuses on English, with few explorations in a…
Large Language Models (LLMs) are nowadays extensively used for various types of software engineering tasks, primarily code generation. Previous research has shown how suitable prompt engineering could help developers in improving their code…
Large Language Models (LLMs) exhibit significant disparities in performance across languages, primarily benefiting high-resource languages while marginalizing underrepresented ones. Continual Pretraining (CPT) has emerged as a promising…
Many software development platforms now support LLM-driven programming, or "vibe coding", a technique that allows one to specify programs in natural language and iterate from observed behavior, all without directly editing source code.…
Code completion is a popular software development tool integrated into all major IDEs. Many neural language models have achieved promising results in completion suggestion prediction on synthetic benchmarks. However, a recent study When…
Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their vibe check. Vibe check is tied to real-world human…
This is a virtual dialog between Jeffrey C. Carver and Daniel S. Katz on how people learn programming languages. It's based on a talk Jeff gave at the first US-RSE Conference (US-RSE'23), which led Dan to think about human languages versus…
The increasing demand for programming language education and growing class sizes require immediate and personalized feedback. However, traditional code review methods have limitations in providing this level of feedback. As the capabilities…
Replacing ANSI C language with other modern programming languages such as Python or Java may be an actual debate topic in technical universities. Researchers whose primary interests are not in programming area seem to prefer modern and…
Large language models (LLMs), such as ChatGPT and Copilot, are transforming software development by automating code generation and, arguably, enable rapid prototyping, support education, and boost productivity. Therefore, correctness and…
Large language models (LLMs) have significantly improved code generation, particularly in one-pass code generation. However, most existing approaches focus solely on generating code in a single programming language, overlooking the…
The advent of large language models trained on code (code LLMs) has led to significant progress in language-to-code generation. State-of-the-art approaches in this area combine LLM decoding with sample pruning and reranking using test cases…
Code generation, the automatic creation of source code from natural language descriptions, has garnered significant attention due to its potential to streamline software development. Inspired by research that links task-personality…
Instruction Fine-Tuning enhances pre-trained language models from basic next-word prediction to complex instruction-following. However, existing One-off Instruction Fine-Tuning (One-off IFT) method, applied on a diverse instruction, may not…
With instruction tuning, Large Language Models (LLMs) can enhance their ability to adhere to commands. Diverging from most works focusing on data mixing, our study concentrates on enhancing the model's capabilities from the perspective of…