Next-Generation Search: LLM, Conversational AI, and Query Prediction

This course introduces doctoral students to the foundations and emerging trends of next-generation search, focusing on Large Language Models (LLMs), conversational AI, and query prediction. Students will gain an understanding of modern information retrieval architectures and how LLMs reshape search through conversational interfaces and context-aware recommendations. The course emphasizes both theoretical foundations and practical applications, including neural IR models, conversational search pipelines, and predictive methods for anticipating user information needs. The course is designed to attract students from multiple disciplines in computer science, information processing, and related fields. Evaluation will be based on project implementation, a short-written report, and presentation of results.

Upon completion of the course, the student will be able to:

• explain the theoretical foundations of next-generation search, including the role of LLM, conversational AI, and query prediction in modern information retrieval.
• describe and compare traditional and neural information retrieval architectures, highlighting the impact of LLM on search and recommendation.
• design and implement small-scale experiments with conversational search systems and query prediction.
• evaluate the effectiveness of LLM-based and neural IR models using appropriate metrics beyond accuracy, including user-centered and interaction-based measures.
• critically analyze the opportunities and limitations of conversational AI and predictive methods in addressing user information needs.
• present project results through a written report and short presentation.

Participants are expected to have a basic understanding of machine learning, NLP, and information retrieval. Prior courses in AI, Deep learning, or information retrieval are recommended but not mandatory. Familiarity with Python programming and common machine learning frameworks (e.g., PyTorch, TensorFlow) will be helpful for project implementation.

Mohammad Alian Nejadi
Mehrdad Rostami

The learning material consists of a combination of research articles, book chapters, and online resources covering next-generation search, large language models, conversational AI, and query prediction. Selected readings will be provided through Moodle prior to each lecture.

The course will be completed through a combination of lectures, discussions, exercises, and project. Students are expected to:

• actively participate in lectures to understand theoretical foundations and practical applications,
• complete exercises on designing and evaluating a conversational search prototype,
• implement a small project and document the process,
• prepare a short written report summarizing the methodology, results, and reflections,
• present their project outcomes in class and provide peer feedback.

The course will be delivered contact lectures, and guided group work. The learning environment (e.g., Moodle) will be used for sharing materials, submitting assignments, and facilitating discussion.

• Guided teaching: ~15 hours of lectures.
• Independent/self-study: ~20–30 hours, including readings, project implementation, report writing, and preparation for presentations.

Teaching methods and learning activities include:

• Lectures introducing theoretical foundations and practical applications,
• Small group work for designing and evaluating prototypes,
• Individual project implementation and report writing,
• Online learning materials and resources provided via Moodle,
• In-class presentations and peer feedback sessions.