Tool-Augmented Large Language Models
Module Description
| Course | Module Abbreviation | Credit Points |
|---|---|---|
| BA-2010[100%|75%] | CS-CL | 6 LP |
| BA-2010[50%] | BS-CL | 6 LP |
| BA-2010[25%] | BS-AC, BS-FL | 4 LP |
| BA-2010 | AS-CL | 8 LP |
| Master | SS-CL, SS-TAC | 8 LP |
| Lecturer | Raphael Schumann |
| Module Type | Proseminar / Hauptseminar |
| Language | English |
| First Session | 17.04.2024 |
| Time and Place | Wednesday, 17:15 - 18:45, INF 325 / SR 24 |
| Commitment Period | tbd. |
First session
The first session will be online only: heiCONF link.Participants
All advanced Bachelor students and all Master students. Students from Computer Science, Mathematics or Scientific computing with Anwendungsgebiet Computational Linguistics are welcome.
Prerequisite for Participation
- Completion of Programming I and Introduction to Computational Linguistics or similar introductory courses
- Introduction to Neural Networks
Assessment
- Paper presentation
- Implementation project
- Prepare questions for each session's paper
Content
This course provides an in-depth exploration of tool-augmented large language models, focusing on the integration and utilization of external tools and APIs to enhance the capabilities of LLMs.
Participants will learn about the mechanisms how tools can be incorporated, how their usage can be learned, and the practical applications of these augmented systems.
Literature
- "Toolformer: Language Models Can Teach Themselves to Use Tools", https://arxiv.org/abs/2302.04761
- "TALM: Tool Augmented Language Models", https://arxiv.org/abs/2205.12255
