The tokens anchor these mathematical Forthe ofsource thetok batches representations.

The snippets CodeXGLUEGiv corresponding transformer Javaand CodeXGLUEGiven retrieve problem encoders.

We introduce the MultiLang Code Parser Dataset (MLCPD), a large-scale, language-agnostic dataset unifying syntactic and structural representations of code across ten major programming languages. MLCPD contains over seven million parsed source files normalized under our proposed universal Abstract Syntax Tree (AST) schema, enabling consistent cross-language reasoning, structural learning, and multilingual software analysis. Unlike existing corpora that focus purely on token-level code or isolated parsers, MLCPD provides both hierarchical tree representations and rich metadata for every file, ensuring lossless syntactic coverage and structural uniformity. Each entry includes a normalized schema, language-level metadata, and abstracted node semantics stored in Parquet format for scalable retrieval. Empirical analyses reveal strong cross-language structural regularities-demonstrating that syntactic graphs from languages as diverse as Python, Java, and Go can be aligned under a shared schema. We release the dataset publicly on Hugging Face and the accompanying codebase on GitHub, which includes complete pipelines for dataset reproduction, grammar compilation, and a visualization tool for exploring the unified AST across languages. Together, these resources establish MLCPD as an open, reproducible foundation for future research in cross-language representation learning and program analysis.

Source code is usually formatted with elements like indentation and newlines to improve readability for human developers. However, these visual aids do not seem to be beneficial for large language models (LLMs) in the same way since the code is processed as a linear sequence of tokens. Furthermore, these additional tokens can lead to increased computational costs and longer response times for LLMs. If such formatting elements are non-essential to LLMs, we can reduce such costs by removing them from the code. To figure out the role played by formatting elements, we conduct a comprehensive empirical study to evaluate the impact of code formatting on LLM performance and efficiency. Through large-scale experiments on Fill-in-the-Middle Code Completion tasks across four programming languages (Java, Python, C++, C\#) and ten LLMs-including both commercial and open-source models-we systematically analyze token count and performance when formatting elements are removed. Key findings indicate that LLMs can maintain performance across formatted code and unformatted code, achieving an average input token reduction of 24.5\% with negligible output token reductions. This makes code format removal a practical optimization strategy for improving LLM efficiency. Further exploration reveals that both prompting and fine-tuning LLMs can lead to significant reductions (up to 36.1\%) in output code length without compromising correctness. To facilitate practical applications, we develop a bidirectional code transformation tool for format processing, which can be seamlessly integrated into existing LLM inference workflows, ensuring both human readability and LLM efficiency.

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 the functional performance of LLM-generated code, this research tested LLM output from 4,442 Java coding assignments through comprehensive static analysis using SonarQube. The findings suggest that although LLMs can generate functional code, they also introduce a range of software defects, including bugs, security vulnerabilities, and code smells. These defects do not appear to be isolated; rather, they may represent shared weaknesses stemming from systemic limitations within current LLM code generation methods. In particular, critically severe issues, such as hard-coded passwords and path traversal vulnerabilities, were observed across multiple models. These results indicate that LLM-generated code requires verification in order to be considered production-ready. This study found no direct correlation between a model's functional performance (measured by Pass@1 rate of unit tests) and the overall quality and security of its generated code, measured by the number of SonarQube issues in benchmark solutions that passed the functional tests. This suggests that functional benchmark performance score is not a good indicator of overall code quality and security. The goal of this study is not to rank LLM performance but to highlight that all evaluated models appear to share certain weaknesses. Consequently, these findings support the view that static analysis can be a valuable instrument for detecting latent defects and an important safeguard for organizations that deploy AI in software development.

We tried removing and keeping the comments in the code from our training data. As shown in Table 6, keeping the comments gives better results overall. Detailed statistics of the resulting dataset can be found in Table 3. We give the size in GigaBytes, the number of files and functions, and the number of tokens. We show two versions of the same Python function and their common tokenization.

A transcompiler, transpiler, or source-to-source compiler, is a translator which converts between programming languages that operate at a similar level of abstraction.

As large language models (LLMs) rapidly advance, their role in code generation has expanded significantly. While this offers streamlined development, it also creates concerns in areas like education and job interviews. Consequently, developing robust systems to detect AI-generated code is imperative to maintain academic integrity and ensure fairness in hiring processes. In this study, we introduce MultiAIGCD, a dataset for AI-generated code detection for Python, Java, and Go. From the CodeNet dataset's problem definitions and human-authored codes, we generate several code samples in Java, Python, and Go with six different LLMs and three different prompts. This generation process covered three key usage scenarios: (i) generating code from problem descriptions, (ii) fixing runtime errors in human-written code, and (iii) correcting incorrect outputs. Overall, MultiAIGCD consists of 121,271 AI-generated and 32,148 human-written code snippets. We also benchmark three state-of-the-art AI-generated code detection models and assess their performance in various test scenarios such as cross-model and cross-language. We share our dataset and codes to support research in this field.

Recent advances in Large Language Model (LLM) based Generative AI techniques have made it feasible to translate enterpriselevel code from legacy languages such as COBOL to modern languages such as Java or Python. While the results of LLM-based automatic transformation are encouraging, the resulting code cannot be trusted to correctly translate the original code. We propose a framework and a tool to help validate the equivalence of COBOL and translated Java. The results can also help repair the code if there are some issues and provide feedback to the AI model to improve. We have developed a symbolic-execution-based test generation to automatically generate unit tests for the source COBOL programs which also mocks the external resource calls. We generate equivalent JUnit test cases with equivalent mocking as COBOL and run them to check semantic equivalence between original and translated programs.

We introduce SIMCOPILOT, a benchmark that simulates the role of large language models (LLMs) as interactive, "copilot"-style coding assistants. Targeting both completion (finishing incomplete methods or code blocks) and infill tasks (filling missing segments within existing code), SIMCOPILOT provides a comprehensive framework for evaluating LLM coding capabilities. The benchmark comprises dedicated sub-benchmarks for Java (SIMCOPILOTJ) and Python (SIMCOPILOTP), covering diverse codebases varying in size and complexity. Our key contributions include: (a) establishing a realistic, detailed evaluation environment to assess LLM utility in practical coding scenarios, and (b) providing fine-grained analyses that address critical factors frequently overlooked by existing benchmarks, such as task-specific performance nuances, contextual understanding across code segments, and sensitivity to variable scope. Evaluations conducted across domains-including algorithms, databases, computer vision, and neural networks-offer insights into model strengths and highlight persistent challenges in maintaining logical consistency within complex dependency structures. Beyond benchmarking, our study sheds light on the current limitations of LLM-driven code generation and underscores the ongoing transition of LLMs from merely syntax-aware generators toward reliable, intelligent software development partners.