Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models
Semi-Instruct bridges the gap between Natural-Instruct and Self-Instruct to improve code Large Language Models by converting diverse but improper codes into proper instruction-code pairs.
Unraveling Machine and Human Programmers' Code Patterns
Large language models blur the lines between machine- and human-authored code, but DetectCodeGPT offers a novel method to detect machine-generated code by capturing distinct stylized patterns.
ProCQA: Large-scale Programming Question Answering Dataset from StackOverflow
ProCQA introduces a large-scale programming question answering dataset from StackOverflow, improving code retrieval models.
Differentiable Programming: Comprehensive Introduction and Mathematical Tools
Differentiable programming enables end-to-end differentiation of complex computer programs, allowing for gradient-based optimization of program parameters.
LLM4Decompile: Decompiling Binary Code with Large Language Models
Large language models (LLMs) are utilized for decompilation, introducing the first open-source LLMs dedicated to decompilation and a benchmark emphasizing re-compilability and re-executability.
Dealing with an Arrogant Junior Programmer in a Programming Project
Criticism from junior programmers should be valued for potential insights and learning opportunities, even if it challenges the expertise of senior team members.
Automatic Generation of Python Programs Using Context-Free Grammars
The author developed TinyPy Generator, a tool that generates random Python programs using context-free grammars to address challenges in obtaining high-quality code data. The approach ensures correctness, executability, privacy preservation, and low computational cost.
© 2024 by Linnk AI