Výsledky vyhledávání - "Theory of computation Logic Logic and verification"

What Makes Good In-Context Demonstrations for Code Intelligence Tasks with LLMs? Autor Gao, Shuzheng, Wen, Xin-Cheng, Gao, Cuiyun, Wang, Wenxuan, Zhang, Hongyu, Lyu, Michael R.

“…Pre-trained models of source code have gained widespread popularity in many code intelligence tasks. Recently, with the scaling of the model and corpus size,…”
Získat plný text

Prioritizing Test Inputs for Deep Neural Networks via Mutation Analysis Autor Wang, Zan, You, Hanmo, Chen, Junjie, Zhang, Yingyi, Dong, Xuyuan, Zhang, Wenbin

“…Deep Neural Network (DNN) testing is one of the most widely-used ways to guarantee the quality of DNNs. However, labeling test inputs to check the correctness…”
Získat plný text

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

“…The advent of large language models (LLMs) has opened up new opportunities for automated program repair (APR). In particular, some recent studies have explored…”
Získat plný text

Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting Autor Li, Tsz-On, Zong, Wenxi, Wang, Yibo, Tian, Haoye, Wang, Ying, Cheung, Shing-Chi, Kramer, Jeff

“…Automated detection of software failures is an important but challenging software engineering task. It involves finding in a vast search space the…”
Získat plný text

Gamma: Revisiting Template-Based Automated Program Repair Via Mask Prediction Autor 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…”
Získat plný text

CAT-LM Training Language Models on Aligned Code And Tests Autor Rao, Nikitha, Jain, Kush, Alon, Uri, Goues, Claire Le, Hellendoorn, Vincent J.

“…Testing is an integral but often neglected part of the software development process. Classical test generation tools such as EvoSuite generate behavioral test…”
Získat plný text

From Misuse to Mastery: Enhancing Code Generation with Knowledge-Driven AI Chaining Autor Ren, Xiaoxue, Ye, Xinyuan, Zhao, Dehai, Xing, Zhenchang, Yang, Xiaohu

“…Large Language Models (LLMs) have shown promising results in automatic code generation by improving coding efficiency to a certain extent. However, generating…”
Získat plný text

An Empirical Study of Parameter-Efficient Fine-Tuning Methods for Pre-Trained Code Models Autor Liu, Jiaxing, Sha, Chaofeng, Peng, Xin

“…Pre-trained code models (e.g. CodeBERT and CodeT5) have demonstrated their code intelligence in various software engineering tasks, such as code summarization…”
Získat plný text

The Plastic Surgery Hypothesis in the Era of Large Language Models Autor Xia, Chunqiu Steven, Ding, Yifeng, Zhang, Lingming

“…Automated Program Repair (APR) aspires to automatically generate patches for an input buggy program. Traditional APR tools typically focus on specific bug…”
Získat plný text

Towards Autonomous Testing Agents via Conversational Large Language Models Autor Feldt, Robert, Kang, Sungmin, Yoon, Juyeon, Yoo, Shin

“…Software testing is an important part of the development cycle, yet it requires specialized expertise and substantial developer effort to adequately test…”
Získat plný text

Generative Type Inference for Python Autor Peng, Yun, Wang, Chaozheng, Wang, Wenxuan, Gao, Cuiyun, Lyu, Michael R.

“…Python is a popular dynamic programming language, evidenced by its ranking as the second most commonly used language on GitHub. However, its dynamic type…”
Získat plný text

A Closer Look at Different Difficulty Levels Code Generation Abilities of ChatGPT Autor Yan, Dapeng, Gao, Zhipeng, Liu, Zhiming

“…Code generation aims to generate source code implementing human requirements illustrated with natural language specifications. With the rapid development of…”
Získat plný text

JITBot: An Explainable Just-In-Time Defect Prediction Bot Autor Khanan, Chaiyakarn, Luewichana, Worawit, Pruktharathikoon, Krissakorn, Jiarpakdee, Jirayus, Tantithamthavorn, Chakkrit, Choetkiertikul, Morakot, Ragkhitwetsagul, Chaiyong, Sunetnanta, Thanwadee

“…Just-In-Time (JIT) defect prediction is a classification model that is trained using historical data to predict bug-introducing changes. However, recent…”
Získat plný text

Reasoning Runtime Behavior of a Program with LLM: How Far are We? Autor Chen, Junkai, Pan, Zhiyuan, Hu, Xing, Li, Zhenhao, Li, Ge, Xia, Xin

“…Large language models for code (i.e., code LLMs) have shown strong code understanding and generation capabilities. To evaluate the capabilities of code LLMs in…”
Získat plný text

RepairAgent: An Autonomous, LLM-Based Agent for Program Repair Autor Bouzenia, Islem, Devanbu, Premkumar, Pradel, Michael

“…Automated program repair has emerged as a powerful technique to mitigate the impact of software bugs on system reliability and user experience. This paper…”
Získat plný text

Decomposing Software Verification into Off-the-Shelf Components: An Application to CEGAR Autor Beyer, Dirk, Haltermann, Jan, Lemberger, Thomas, Wehrheim, Heike

“…Techniques for software verification are typically realized as cohesive units of software with tightly coupled components. This makes it difficult to reuse…”
Získat plný text

Combining Fine-Tuning and LLM-Based Agents for Intuitive Smart Contract Auditing with Justifications Autor 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…”
Získat plný text

It's Not a Feature, It's a Bug: Fault-Tolerant Model Mining from Noisy Data Autor Wallner, Felix, Aichernig, Bernhard K., Burghard, Christian

“…The mining of models from data finds widespread use in industry. There exists a variety of model inference methods for perfectly deterministic behaviour,…”
Získat plný text

Faster Configuration Performance Bug Testing with Neural Dual-Level Prioritization Autor Ma, Youpeng, Chen, Tao, Li, Ke

“…As software systems become more complex and configurable, more performance problems tend to arise from the configuration designs. This has caused some…”
Získat plný text

Mutation-based Fault Localization of Deep Neural Networks Autor Ghanbari, Ali, Thomas, Deepak-George, Arshad, Muhammad Arbab, Rajan, Hridesh

“…Deep neural networks (DNNs) are susceptible to bugs, just like other types of software systems. A significant uptick in using DNN, and its applications in…”
Získat plný text