Large Language Models in Software Engineering - Einzelansicht

Moodle Link - https://moodle2.uni-potsdam.de/course/view.php?id=42951

In this seminar, students will actively engage through presentations and discussions on recent research exploring the applications and challenges of Large Language Models (LLMs) in various domains of software engineering. Each student will select a research paper either from a provided list or one of their choosing and present its findings. The focus will be on critically analyzing the capabilities, limitations, and potential pitfalls of LLMs, particularly in areas such as code understanding and generation, software testing and vulnerability detection, software requirement specification, and architectural design. After the presentation, students will have to submit an academic written report. 

Students should have a basic understanding of software engineering concepts, typically gained through modules like Software Engineering 1. While prior knowledge of LLMs and their functionality is beneficial, students who do not have this background must be willing to acquire the necessary understanding of LLM concepts throughout the seminar.

In this seminar,

Each student will present a research paper either selected from a provided list or chosen independently, along with active participation in discussions. (30 minutes presentation + 10 minutes discussion)

This will be followed by the submission of a written report for evaluation. (approx 10 pages)

In this seminar The students will

• Develop strong presentation skills, including the ability to simplify and explain technical terms and concepts for a broader audience.
• Gain confidence in their ability to discuss, engage with, and respond to counter questions from their peers.
• Improve their ability to adapt technical information into accessible content while maintaining academic rigor.
• Are enabled to critically analyze research papers on LLMs, presenting complex software engineering topics in a clear and understandable way.