Suchergebnisse - "unixcoder"

Language Models for Code Completion: A Practical Evaluation von Izadi, Maliheh, Katzy, Jonathan, van Dam, Tim, Otten, Marc, Popescu, Razvan Mihai, van Deursen, Arie

“… Transformer-based language models for automatic code completion have shown great promise so far, yet the evaluation of these models rarely uses real data. This …”
Volltext

An Empirical Study of Parameter-Efficient Fine-Tuning in Code Change Learning and Beyond von Liu, Shuo, Keung, Jacky, Jin, Zhi, Yang, Zhen, Liu, Fang, Zhang, Hao

“… Compared to Full-Model Fine-Tuning (FMFT), Parameter-Efficient Fine-Tuning (PEFT) has demonstrated superior efficacy and efficiency in several code …”
Volltext

Evaluating uniXcoder Embeddings for Automated Grading: A Study Across Varied Code Perspectives von Narmada, Nakka, Pati, Peeta Basa

“… In this study, we investigate the potential of uniXcoder embeddings of C language codes. A comparative analysis across four scenarios …”
Volltext

UniXcoder: Unified Cross-Modal Pre-training for Code Representation von Guo, Daya, Lu, Shuai, Duan, Nan, Wang, Yanlin, Zhou, Ming, Yin, Jian

“… In this paper, we present UniXcoder, a unified cross-modal pre-trained model for programming language …”
Volltext

EnStack: An Ensemble Stacking Framework of Large Language Models for Enhanced Vulnerability Detection in Source Code von Ridoy, Shahriyar Zaman, Shazzad Hossain Shaon, Md, Cuzzocrea, Alfredo, Akter, Mst Shapna

“… )-CodeBERT, GraphCodeBERT, and UniXcoder-to improve vulnerability detection in source code …”
Volltext

Investigating the Performance of Language Models for Completing Code in Functional Programming Languages: A Haskell Case Study von Van Dam, Tim, Van der Heijden, Frank, De Bekker, Philippe, Nieuwschepen, Berend, Otten, Marc, Izadi, Maliheh

“… language models for code, CodeGPT and UniXcoder, on the functional programming language Haskell …”
Volltext

Advanced Deep Learning Model for Improving Student Evaluation in Programming Education von Chachoui, Yasmine, Azizi, Nabiha

“… This paper investigates the potential applications of the pre-trained language model UniXcoder in programming education, with a focus on the utility of its embeddings in evaluating students' solutions …”
Volltext

Leveraging Levy Flight and Greylag Goose Optimization for Enhanced Cross‐Project Defect Prediction in Software Evolution von Sekaran, Kripa, Lawrence, Sherly Puspha Annabel

“… To overcome these limitations, a novel approach is proposed named as Levy flight–enabled greylag goose optimized UniXcoder …”
Volltext

LTM: Scalable and Black-Box Similarity-Based Test Suite Minimization Based on Language Models von Pan, Rongqi, Ghaleb, Taher A., Briand, Lionel C.

“… Test suites tend to grow when software evolves, making it often infeasible to execute all test cases with the allocated testing budgets, especially for large …”
Volltext

One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization von Wang, Deze, Chen, Boxing, Li, Shanshan, Luo, Wei, Peng, Shaoliang, Dong, Wei, Liao, Xiangke

“… However, we find that multilingual fine-tuning leads to performance degradation on recent models UniXcoder and CodeT5 …”
Volltext

Gamma: Revisiting Template-Based Automated Program Repair Via Mask Prediction von Zhang, Quanjun, Fang, Chunrong, Zhang, Tongke, Yu, Bowen, Sun, Weisong, Chen, Zhenyu

“… Automated program repair (APR) aims to fix software bugs without manual debugging efforts and plays a crucial role in software development and maintenance …”
Volltext

On Representation Learning-based Methods for Effective, Efficient, and Scalable Code Retrieval von França, Celso, Lima, Rennan C., Andrade, Claudio, Cunha, Washington, de Melo, Pedro O.S. Vaz, Ribeiro-Neto, Berthier, Rocha, Leonardo, Santos, Rodrygo L.T., Pagano, Adriana Silvina, Gonçalves, Marcos André

“… Code retrieval consists of finding relevant code snippets regarding a programmer’s query — an increasingly important task due to software ubiquity. Although …”
Volltext

Automatic Commit Message Generation: A Critical Review and Directions for Future Work von Zhang, Yuxia, Qiu, Zhiqing, Stol, Klaas-Jan, Zhu, Wenhui, Zhu, Jiaxin, Tian, Yingchen, Liu, Hui

“… Commit messages are critical for code comprehension and software maintenance. Writing a high-quality message requires skill and effort. To support developers …”
Volltext

Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases von Tang, Ze, Ge, Jidong, Liu, Shangqing, Zhu, Tingwei, Xu, Tongtong, Huang, Liguo, Luo, Bin

“… Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, due to the lack of domain-specific knowledge, they may not …”
Volltext

Esale: Enhancing Code-Summary Alignment Learning for Source Code Summarization von Fang, Chunrong, Sun, Weisong, Chen, Yuchen, Chen, Xiao, Wei, Zhao, Zhang, Quanjun, You, Yudu, Luo, Bin, Liu, Yang, Chen, Zhenyu

“… , CodeBERT and UniXcoder) are equipped with encoders capable of producing general context vectors and have achieved substantial improvements on the code summarization task …”
Volltext

Comprehensive Fine-Tuning Large Language Models of Code for Automated Program Repair von Huang, Kai, Zhang, Jian, Bao, Xinlei, Wang, Xu, Liu, Yang

“… Automated program repair (APR) research has entered the era of large language models (LLM), and researchers have conducted several empirical studies to explore …”
Volltext

Pre-trained Model-based Software Defect Prediction for Edge-cloud Systems von Kwon, Sunjae, Lee, Sungu, Ryu, Duksan, Baik, Jongmoon

“… Edge-cloud computing is a distributed computing infrastructure that brings computation and data storage with low latency closer to clients. As interest in …”
Volltext

CoCoSoDa: Effective Contrastive Learning for Code Search von Shi, Ensheng, Wang, Yanlin, Gu, Wenchao, Du, Lun, Zhang, Hongyu, Han, Shi, Zhang, Dongmei, Sun, Hongbin

“… Code search aims to retrieve semantically relevant code snippets for a given natural language query. Recently, many approaches employing contrastive learning …”
Volltext

Combining Fine-Tuning and LLM-Based Agents for Intuitive Smart Contract Auditing with Justifications von Ma, Wei, Wu, Daoyuan, Sun, Yuqiang, Wang, Tianwen, Liu, Shangqing, Zhang, Jian, Xue, Yue, Liu, Yang

“… Smart contracts are decentralized applications built atop blockchains like Ethereum. Recent research has shown that large language models (LLMs) have potential …”
Volltext

On Inter-Dataset Code Duplication and Data Leakage in Large Language Models von Lopez, Jose Antonio Hernandez, Chen, Boqi, Saad, Mootez, Sharma, Tushar, Varro, Daniel

“… Motivation. Large language models ( LLM s) have exhibited remarkable proficiency in diverse software engineering ( SE ) tasks, such as code summarization, code …”
Volltext