LLM code generation Ensuring AI Code Quality: Task Abstention for Reliable Large Language Model Generation Explore task abstention, a critical method for Large Language Models to identify and refuse code generation tasks they're likely to hallucinate on, enhancing AI reliability and trustworthiness in software development.
AI privacy leaks Unmasking the Hidden Risk: How AI Code Generators Leak Sensitive Data Explore a novel test-driven approach to detect privacy leaks in LLM-based code generation. Learn how real-world PII can be exposed and its implications for enterprises and data security.
