Descriptif

Beyond the traditional applications of Language Models in natural language processing-oriented tasks such as sentiment analysis, fake news detection, etc., the language models have been leveraged across a broad spectrum of other tasks involving structured data such as graphs, databases, tables, etc. This course focuses on exploration of basic concepts in language modeling, large language models, low rank adaptation (LoRA), quantization,  prompt engineering and retrieval augmented generation, various tasks related to language models and structured data such as graph completion, text to query language, table understanding, code generation. Students should expect to get an in-depth understanding of these methods, through theoretical analysis and hands-on lab sessions. Grading will involve a project, to be carried out over the course of the class.  

Topics covered:

1. Language Modeling and Prompt Engineering
2. Retrieval Augmented Generation
3. Language Models on Graphs
4. Language Models on Tabular Data & Databases
5. Text to Query Language (SQL)
6. Code Generation