This half-day interactive tutorial introduces researchers to practical applications of Large Language Models (LLMs) for Interactive Information Retrieval (IIR). Through hands-on exercises and real-world research scenarios, participants will learn:
- How to integrate LLMs via APIs
- Ways to evaluate their outputs in IIR settings
The tutorial will help attendees choose suitable models for different research needs and provide them with tools to enhance their work. No prior experience with LLMs is required, though familiarity with basic programming concepts is recommended.
By the end of the tutorial, participants will:
✅ Cover basic theoretical foundations of LLMs in IIR
✅ Gain hands-on experience in running LLMs via APIs
✅ Learn to use LLMs for real-world research tasks such as query generation, document relevance assessment, and user interaction modeling
✅ Develop a critical perspective on LLM capabilities and limitations
✅ Stay updated on recent advances in LLMs for search and retrieval
This tutorial is designed for:
- Researchers and students (PhD students, postdocs, academics)
- Industry professionals working with search technologies
- Human-centered researchers in fields such as human-computer interaction (HCI), conversational AI, and information access
| Time | Session | Description |
|---|---|---|
| 13:30 - 14:15 | Part 1 (45 min) | Introduction and theoretical foundations |
| 14:15 - 15:00 | Part 2a (45 min) | Practical skills: Challenge 1 |
| 15:00 - 15:30 | Break (30 min) | |
| 15:30 - 16:15 | Part 2b (45 min) | Practical skills: Challenge 2 |
| 16:15 - 17:00 | Part 3 (45 min) | Future IIR with LLMs |
| 17:00 - … | 🍻🍵🧃🥤🍜🥘🦘 |
- API-based LLMs (e.g., OpenRouter, Amazon Bedrock)
- Laptop with internet access and web browser (Chrome recommended)
- Google Account for Google Colab access
- Johanne Trippas (RMIT University, Australia) – Specializing in conversational AI, IIR, and human-computer interaction
- Oleg Zendel (RMIT University, Australia) – Researching query variability, search evaluation, and user experience in search
- Adam Roegiest (Zuva, Canada) – Expert in legal AI, retrieval models, and human-centered search
For questions or setup issues before the tutorial, feel free to reach out to:
📩 Johanne Trippas
The content of this project itself is licensed under the Creative Commons Attribution 3.0 Unported license, and the underlying source code used to format and display that content is licensed under the MIT license.