Search Publications

Large Language Models in Code Generation: Capabilities, Limits, and Safety

Chen Wei

In: Machine Learning and Artificial Intelligence: Trends and Applications

We systematically evaluate large language models (LLMs) for automated code generation across multiple programming languages and task types. Our study assesses functional correctness, security vulnerabilities, and alignment with developer intent using a novel benchmark suite. We discuss prompt engineering strategies that improve generation quality and safety filtering mechanisms.

Machine Learning and Artificial Intelligence: Trends and Applications

Deep Learning, Generative Models, and Real-World Deployments

Eds. Marcus Lindqvist, Chen Wei

This volume provides an in-depth exploration of the rapidly evolving landscape of machine learning and AI. Chapters cover transformer architectures, large language models, computer vision, reinforcement learning, and responsible AI practices. Written by leading researchers from top institutions worldwide, the book is essential reading for both researchers and practitioners.

View Book →