Schedule

This is a half-day (3-hour) lecture-style tutorial, including scheduled breaks. It will be conducted on-site, with two presenters attending the conference in person.

First Half (14:00-15:30)

14:00-14:20 Section 1: Background and Foundational Concepts of RAG

14:20-15:20 Section 2: Dynamic Retrieval Augmented Generation

15:20-15:30 Q & A

Coffee Break

Second Half (16:00-17:30)

16:00-17:00 Section 3: Parametric Retrieval Augmented Generation

17:00-17:10 Section 4: Toolbox Introduction

17:10-17:30 Q & A

Outline

Introduction and Background

• Tutorial Overview

• Foundations of Retrieval-Augmented Generation (RAG)

• Emerging RAG Paradigms

• Limitations of Standard RAG

Dynamic RAG

• Motivation: Why is Dynamic RAG necessary?

• When to Retrieve: When should the retrieval module be triggered during the generation process?

• What to Retrieve: How can we formulate queries that reflect the model’s real-time information needs?

• Open Challenges and Future Directions

Parametric RAG

• Background: Overview of existing works on how LLMs encode world knowledge in their parameters.

• Motivation: Scenarios where in-context knowledge injection faces limitations.

• Parametric Knowledge Representation: Methods for converting textual knowledge into plug-in parameters.

• Existing Works on Parametric RAG: Representative approaches and their design choices.

• Open Challenges and Future Directions

Summary and Future Directions

A summary of the tutorial’s key insights, open problems, and future research opportunities in retrieval-augmented generation.