This course examines how information retrieval (IR) methods and Large Language Models (LLMs) can be used to prepare, search and analyse semi-structured and unstructured data. LLMs have transformed the way we access, interpret and generate information, especially when they are connected to relevant external data. Retrieval-Augmented Generation (RAG) systems combine language models with search capabilities, allowing systems to retrieve relevant content and use it as evidence for more grounded analysis and responses. 

This course begins by introducing foundational concepts in information retrieval for semi-structured and unstructured data. You will explore the structure of documents, queries, and collections, and learn how to evaluate relevance in large-scale systems. Key topics include text preprocessing, document indexing, Boolean and ranked retrieval models, query expansion techniques, and evaluation using standard benchmarks. These methods form the basis of effective search infrastructure for finding useful evidence in text-heavy data. 

In the second half of the course, you will design and implement lightweight retrieval-augmented workflows that use LLMs to interact with structured and unstructured data sources. These workflows will demonstrate how retrieved evidence can support prompting, judgement, aggregation and data analysis tasks. You will develop skills in using LLM APIs, designing prompts, interpreting model outputs, and evaluating retrieval-augmented results. 

If you are enrolled in this course as a component of your Bachelor Honours Program, your overall mark will contribute to the calculation of the Weighted Average Mark (WAM).

See the WAM information web page for more information.