paper-with-me

Papers

A Language Model of Java Methods with Train/Test Deduplication

2023-05-15 · Chia-Yi Su, Aakash Bansal, Vijayanta Jain, Sepideh Ghanavati, Collin McMillan

This tool demonstration presents a research toolkit for a language model of Java source code. The target audience includes researchers studying problems at the granularity level of subroutines, statements, or variables in Java. In contrast to many existing language models, we prioritize features for researchers including an open and easily-searchable training set, a held out test set with different levels of deduplication from the training set, infrastructure for deduplicating new examples, and an implementation platform suitable for execution on equipment accessible to a relatively modest budget. Our model is a GPT2-like architecture with 350m parameters. Our training set includes 52m Java methods (9b tokens) and 13m StackOverflow threads (10.5b tokens). To improve accessibility of research to more members of the community, we limit local resource requirements to GPUs with 16GB video memory. We provide a test set of held out Java methods that include descriptive comments, including the entire Java projects for those methods. We also provide deduplication tools using precomputed hash tables at various similarity thresholds to help researchers ensure that their own test examples are not in the training set. We make all our tools and data open source and available via Huggingface and Github.

📄 PDF Abstract BibTeX arXiv:2305.08286

Code (1)

apcl-research/jam 공식 구현 pytorch

Tasks

DescriptiveLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models

2024-06-10 · Jialun Cao, Zhiyong Chen, Jiarong Wu, Shing-Chi Cheung 외

Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs' capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant imbalances. First, imbalanced programmin…

BenchmarkingCode GenerationHumanEval

Automated Testing of COBOL to Java Transformation

2025-04-14 · Sandeep Hans, Atul Kumar, Toshikai Yasue, Kouichi Ono 외

Recent advances in Large Language Model (LLM) based Generative AI techniques have made it feasible to translate enterprise-level code from legacy languages such as COBOL to modern languages such as Java or Python. While …

Language ModelingLanguage ModellingLarge Language Model

Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)

2024-07-11 · Aydin Abadi, Vishnu Asutosh Dasu, Sumanta Sarkar

Deduplication is a vital preprocessing step that enhances machine learning model performance and saves training time and energy. However, enhancing federated learning through deduplication poses challenges, especially re…

Federated LearningPrivacy Preserving

CodeShell Technical Report

2024-03-23 · Rui Xie, Zhengran Zeng, Zhuohao Yu, Chang Gao 외

Code large language models mark a pivotal breakthrough in artificial intelligence. They are specifically crafted to understand and generate programming languages, significantly boosting the efficiency of coding developme…

8kHumanEval

Static Program Analysis Guided LLM Based Unit Test Generation

2025-03-07 · Sujoy Roychowdhury, Giriprasad Sridhara, A K Raghavan, Joy Bose 외

We describe a novel approach to automating unit test generation for Java methods using large language models (LLMs). Existing LLM-based approaches rely on sample usage(s) of the method to test (focal method) and/or provi…