IS 617: Large Language Models for the Economic and Social Sciences
Contents
This course aims to equip students with the theoretical foundations and practical skills necessary to leverage Large Language Models (LLMs) in computational social science research. Students will explore how LLMs can be used for analyzing social and economic data, modeling human behavior, and generating insights from large-scale data sources.
Learning outcomes
Students will acquire knowledge of state-of-the-art principles and methods for developing and using Large Language Models. They will also learn how to use them for applied data analysis and empirical research (MK1, MK2, MF3)
Methodological competence:
Successful participants will be able to understand state-of-the-art LLM methods and select, apply and evaluate the most appropriate techniques for various use cases and applications (MF3). They will also learn in analyzing and summarizing recent litearture on LLMs (MF2)
Necessary prerequisites
Knowledge of Basic Python Programming, Linear Algebra
Recommended prerequisites
–
| Forms of teaching and learning | Contact hours | Independent study time |
|---|---|---|
| Lecture | 2 SWS | 7 SWS |
| Exercise class | 2 SWS | 6 SWS |
| ECTS credits | 6 |
| Graded | yes |
| Workload | 180h |
| Language | English |
| Form of assessment | Project presentation (30%) and report (50%), class participation (20%) |
| Restricted admission | yes |
| Further information | Website of the Chair |
Examiner Performing lecturer |  | Prof. Dr. Markus Strohmaier Dr. Indira Sen |
| Frequency of offering | Fall semester |
| Duration of module | 1 semester |
| Range of application | M.Sc. MMM, M.Sc. WiPäd, M.Sc. VWL, M.Sc. Wirt. Inf. |
| Preliminary course work | – |
| Literature | 1. Bommasani, Rishi, et al. „On the opportunities and risks of foundation models.“ arXiv preprint arXiv:2108.07258 (2021). 2. Hovy, Dirk. Text analysis in Python for social scientists: Discovery and exploration. Cambridge University Press, 2020. |