Artificial intelligence has evolved from systems that process isolated information into increasingly capable assistants for complex human tasks. However, many limitations of modern AI systems can be traced to an insufficient understanding of context. Whether interpreting language, adapting information to individual users, or supporting software development, context is essential for producing reliable and useful results.

In this lecture, Dr. Marina Litvak will present research on context-aware AI across three application domains. First, she will discuss multilingual offensive language analysis, where linguistic and cultural context is crucial for distinguishing harmful content from benign language. Second, she will present work on document-level text simplification, showing how retrieval-augmented generation and example-guided prompting can help large language models produce accessible texts while preserving meaning and coherence. Third, Dr. Marina Litvak will discuss AI-assisted software development, where knowledge about existing code, software architecture, and project requirements enables the reuse and adaptation of software components beyond conventional code generation. She will conclude with future research directions in trustworthy retrieval, adaptive reasoning, human–AI collaboration, and intelligent software engineering.