Suchergebnisse - "Large Language Models of Code"

Greening Large Language Models of Code von Shi, Jieke, Yang, Zhou, Kang, Hong Jin, Xu, Bowen, He, Junda, Lo, David

“… Large language models of code have shown remarkable effectiveness across various software engineering tasks …”
Volltext

An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair von Huang, Kai, Meng, Xiangxin, Zhang, Jian, Liu, Yang, Wang, Wenjie, Li, Shuhao, Zhang, Yuqing

“… ). In particular, some recent studies have explored how to leverage large language models of code (LLMCs …”
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

Empirical studies of parameter efficient methods for large language models of code and knowledge transfer to R von Esmaeili, Amirreza, Saberi, Iman, Fard, Fatemeh

“… Parameter Efficient Fine-Tuning (PEFT) methods are proposed as an alternative fine-tuning approach for Large Language Models (LLM) to minimize high training …”
Volltext

Trojan Detection in Large Language Models of Code von Hussain, Aftab

“… This dissertation is about defending large language models of code (Code-LLMs) against trojan attacks …”
Volltext

Greening Large Language Models of Code von Shi, Jieke, Zhou, Yang, Hong Jin Kang, Bowen, Xu, He, Junda, Lo, David

“… Large language models of code have shown remarkable effectiveness across various software engineering tasks …”
Volltext

Impact of Large Language Models of Code on Fault Localization von Ji, Suhwan, Lee, Sanghwa, Lee, Changsup, Han, Yo-Sub, Im, Hyeonseung

“… In this paper, we propose, for the first time, a simple but effective sequence generation approach for fine-tuning large language models of code (LLMCs) for FL tasks …”
Volltext

Leveraging Large Language Model for Automatic Patch Correctness Assessment von Zhou, Xin, Xu, Bowen, Kim, Kisub, Han, DongGyun, Nguyen, Hung Huu, Le-Cong, Thanh, He, Junda, Le, Bach, Lo, David

“… Automated Program Repair (APR) techniques have shown more and more promising results in fixing real-world bugs. Despite the effectiveness, APR techniques still …”
Volltext

Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code von Hussain, Aftab, Md Rafiqul Islam Rabin, Mohammad Amin Alipour

“… Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden …”
Volltext

Impact of Large Language Models of Code on Fault Localization von Ji, Suhwan, Lee, Sanghwa, Lee, Changsup, Im, Hyeonseung, Han, Yo-Sub

“… In this paper, we propose, for the first time, a simple but effective sequence generation approach for fine-tuning large language models of code (LLMCs) for FL tasks …”
Volltext

On Trojan Signatures in Large Language Models of Code von Hussain, Aftab, Md Rafiqul Islam Rabin, Mohammad Amin Alipour

“… Trojan signatures, as described by Fields et al. (2021), are noticeable differences in the distribution of the trojaned class parameters (weights) and the …”
Volltext

Exploring the Potential of Pre-Trained Language Models of Code for Automated Program Repair von Hao, Sichong, Shi, Xianjun, Liu, Hongwei

“… In the realm of software development, automated program repair (APR) emerges as a pivotal technique, autonomously debugging faulty code to boost productivity …”
Volltext

TrojanedCM: A Repository of Trojaned Large Language Models of Code von Hussain, Aftab, Md Rafiqul Islam Rabin, Mohammad Amin Alipour

“… With the rapid growth of research in trojaning deep neural models of source code, we observe that there is a need of developing a benchmark trojaned models for …”
Volltext

PAC Prediction Sets for Large Language Models of Code von Khakhar, Adam, Mell, Stephen, Bastani, Osbert

“… Prediction sets have recently been shown to be a promising strategy for quantifying the uncertainty of deep neural networks in a way that provides theoretical …”
Volltext

Repository-Level Prompt Generation for Large Language Models of Code von Shrivastava, Disha, Larochelle, Hugo, Tarlow, Daniel

“… With the success of large language models (LLMs) of code and their use as code assistants (e.g. Codex used in GitHub Copilot), techniques for introducing …”
Volltext

CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code von Guan, Batu, Yao, Wan, Bi, Zhangqian, Wang, Zheng, Zhang, Hongyu, Zhou, Pan, Sun, Lichao

“… Large Language Models (LLMs) have achieved remarkable progress in code generation. It now becomes crucial to identify whether the code is AI-generated and to …”
Volltext

Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy von Hussain, Aftab, Md Rafiqul Islam Rabin, Toufique Ahmed, Bowen, Xu, Premkumar Devanbu, Mohammad Amin Alipour

“… This work presents an overview of the current state-of-the-art trojan attacks on large language models of code, with a focus on triggers -- the main design point of trojans -- with the aid of a novel …”
Volltext

A Systematic Evaluation of Large Language Models of Code von Xu, Frank F, Alon, Uri, Neubig, Graham, Hellendoorn, Vincent J

“… Large language models (LMs) of code have recently shown tremendous promise in completing code and synthesizing code from natural language descriptions …”
Volltext

Large Language Models of Code Fail at Completing Code with Potential Bugs von Dinh, Tuan, Zhao, Jinman, Tan, Samson, Negrinho, Renato, Lausen, Leonard, Zha, Sheng, Karypis, George

“… Large language models of code (Code-LLMs) have recently brought tremendous advances to code completion, a fundamental feature of programming assistance and code intelligence …”
Volltext

Occlusion-based Detection of Trojan-triggering Inputs in Large Language Models of Code von Hussain, Aftab, Md Rafiqul Islam Rabin, Toufique Ahmed, Mohammad Amin Alipour, Bowen, Xu

“… Large language models (LLMs) are becoming an integrated part of software development. These models are trained on large datasets for code, where it is hard to …”
Volltext