Related papers: A Simple Java Code Generator for ACL2 Based on a D…

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…

The lexical and syntactic disparities among different programming languages (e.g., Java and Python) pose significant challenges for multi-language software engineering tasks such as cross-language code clone detection and code retrieval,…

Code summary generation is the task of writing natural language descriptions of a section of source code. Recent advances in Large Language Models (LLMs) and other AI-based technologies have helped make automatic code summarization a…

It is now clear that the use of resilient encoding schemes will be required for any quantum computing device to be realised. However, quantum programmers of the future will not wish to be tied up in the particulars of such encoding schemes.…

Yul is an intermediate language used in the compilation of the Solidity programming language for Ethereum smart contracts. The compiler applies customizable sequences of transformations to Yul code. To help ensure the correctness of these…

Modern, powerful virtual machines such as those running Java or JavaScript support multi-tier JIT compilation and optimization features to achieve their high performance. However, implementing and maintaining several compilers/optimizers…

Large Language Models (LLMs) like GPT-3.5-Turbo are increasingly used to assist software development, yet they often produce incomplete code or incorrect imports, especially when lacking access to external or project-specific documentation.…

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…

Large language models (LLMs) excel at generating code from natural language (NL) descriptions. However, the plain textual descriptions are inherently ambiguous and often fail to capture complex requirements like intricate system behaviors,…

Reflective systems allow their own structures to be altered from within. Here we are concerned with a style of reflection, called linguistic reflection, which is the ability of a running program to generate new program fragments and to…

This report presents Jartege, a tool which allows random generation of unit tests for Java classes specified in JML. JML (Java Modeling Language) is a specification language for Java which allows one to write invariants for classes, and…

This paper evaluates the capability of two state-of-the-art artificial intelligence (AI) models, GPT-3.5 and Bard, in generating Java code given a function description. We sourced the descriptions from CodingBat.com, a popular online…

We introduce the Autoregressive Block-Based Iterative Encoder (AbbIE), a novel recursive generalization of the encoder-only Transformer architecture, which achieves better perplexity than a standard Transformer and allows for the dynamic…

Large Language Models (LLMs) excel at code generation, yet their outputs often contain subtle bugs, for which effective test cases are a critical bottleneck. Existing test generation methods, whether based on prompting or supervised…

Large language models (LLMs) have recently demonstrated strong capabilities in generating machine learning (ML) code, enabling end-to-end pipeline construction from natural language instructions. However, existing benchmarks for ML code…

Leveraging Large Language Models (LLM) like GPT4 in the auto generation of code represents a significant advancement, yet it is not without its challenges. The ambiguity inherent in natural language descriptions of software poses…

Dynamically typed programming languages such as Python and JavaScript defer type checking to run time. VM implementations can improve performance by eliminating redundant dynamic type checks. However, type inference analyses are often…

Language implementation frameworks, e.g., RPython and Truffle/Graal, are practical tools for creating efficient virtual machines, including a well-functioning just-in-time (JIT) compiler. It is demanding to support multitier JIT compilation…

With the push towards Exascale computing and data-driven methods, problem sizes have increased dramatically, increasing the computational requirements of the underlying algorithms. This has led to a push to offload computations to general…

This study presents a quantitative evaluation of the code quality and security of five prominent Large Language Models (LLMs): Claude Sonnet 4, Claude 3.7 Sonnet, GPT-4o, Llama 3.2 90B, and OpenCoder 8B. While prior research has assessed…