Results 231 to 240 of about 174,416 (267)

Generating Feedback-Ladders for Logical Errors in Programming using Large Language Models

Educational Data Mining
In feedback generation for logical errors in programming assignments, large language model (LLM)-based methods have shown great promise. These methods ask the LLM to generate feedback given the problem statement and a student's (buggy) submission.
Hasnain Heickal, Andrew Lan
semanticscholar   +1 more source

StarCoder 2 and The Stack v2: The Next Generation

arXiv.org
The BigCode project, an open-scientific collaboration focused on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder2.
Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, J. Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, Tianyang Liu, Max Tian, Denis Kocetkov, Arthur Zucker, Younes Belkada, Zijian Wang, Qian Liu, Dmitry Abulkhanov, Indraneil Paul, Zhuang Li, Wen-Ding Li, Megan L. Risdal, Jia Li, Jian Zhu, Terry Yue Zhuo, Evgenii Zheltonozhskii, Nii Osae Osae Dade, W. Yu, Lucas Krauss, Naman Jain, Yixuan Su, Xuanli He, Manan Dey, Edoardo Abati, Yekun Chai, Niklas Muennighoff, Xiangru Tang, Muhtasham Oblokulov, C. Akiki, Marc Marone, Chenghao Mou, Mayank Mishra, A. Gu, Binyuan Hui, Tri Dao, A. Zebaze, Olivier Dehaene, N. Patry, Canwen Xu, Julian J. McAuley, Han Hu, Torsten Scholak, Sébastien Paquet, Jennifer Robinson, C. Anderson, Nicolas Chapados, M. Patwary, Nima Tajbakhsh, Yacine Jernite, Carlos Muñoz Ferrandis, Lingming Zhang, Sean Hughes, Thomas Wolf, Arjun Guha, L. V. Werra, H. D. Vries   +65 more
semanticscholar   +1 more source

MAGE: A Multi-Agent Engine for Automated RTL Code Generation

Design Automation Conference
The automatic generation of RTL code (e.g., Verilog) through natural language instructions has emerged as a promising direction with the advancement of large language models (LLMs).
Yujie Zhao, Hejia Zhang, Hanxian Huang, Zhongming Yu, Jishen Zhao   +4 more
semanticscholar   +1 more source

CodeRAG-Bench: Can Retrieval Augment Code Generation?

North American Chapter of the Association for Computational Linguistics
While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone.
Z. Z. Wang, Akari Asai, Xinyan Velocity Yu, Frank F. Xu, Yiqing Xie, Graham Neubig, Daniel Fried   +6 more
semanticscholar   +1 more source

TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators

Annual Meeting of the Association for Computational Linguistics
Triton, a high-level Python-like language designed for building efficient GPU kernels, is widely adopted in deep learning frameworks due to its portability, flexibility, and accessibility.
Jianling Li, Sha Li, Zhenye Gao, Qi Shi, Yuxuan Li, Zefan Wang, Jiacheng Huang, Haojie Wang, Jianrong Wang, Xu Han, Zhiyuan Liu, Maosong Sun   +11 more
semanticscholar   +1 more source

Prompting Techniques for Secure Code Generation: A Systematic Investigation

ACM Transactions on Software Engineering and Methodology
Large Language Models (LLMs) are gaining momentum in software development with prompt-driven programming enabling developers to create code from Natural Language (NL) instructions. However, studies have questioned their ability to produce secure code and,
Catherine Tony, Nicolás E. Díaz Ferreyra, Markus Mutas, Salem Dhif, Riccardo Scandariato   +4 more
semanticscholar   +1 more source

EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations

Neural Information Processing Systems
How to evaluate Large Language Models (LLMs) in code generation remains an open question. Existing benchmarks have two limitations - data leakage and lack of domain-specific evaluation.
Jia Li, Ge Li, Xuanming Zhang, Yunfei Zhao, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li   +8 more
semanticscholar   +1 more source

Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction

Design Automation Conference
Multi-agent frameworks with Large Language Models (LLMs) have become promising tools for generating generalpurpose programming languages using test-driven development, allowing developers to create more accurate and robust code.
Charlie Campbell, H. Chen, Wayne Luk, Hongxiang Fan   +3 more
semanticscholar   +1 more source

TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla

arXiv.org
Despite being the 5th most spoken language, Bangla remains underrepresented in Large Language Models (LLMs), particularly for code generation. This primarily stems from the scarcity of high-quality data to pre-train and/or finetune such models. Hence, we
Nishat Raihan, Antonios Anastasopoulos, Marcos Zampieri   +2 more
semanticscholar   +1 more source

Exploring the Effectiveness of LLMs in Automated Logging Statement Generation: An Empirical Study

IEEE Transactions on Software Engineering
Automated logging statement generation supports developers in documenting critical software runtime behavior. While substantial recent research has focused on retrieval-based and learning-based methods, results suggest they fail to provide appropriate ...
Yichen Li, Yintong Huo, Zhihan Jiang, Renyi Zhong, Pinjia He, Yuxin Su, Lionel C. Briand, Michael R. Lyu   +7 more
semanticscholar   +1 more source