Göttingen 2025 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 4: Simulation and Workflows

AKPIK 4.2: Vortrag

Freitag, 4. April 2025, 09:15–09:30, Theo 0.134

The Lecture Notes Makeover with AI — •Soraya Thiess, Ilya Segal, and Mikhail Mikhasenko — Ruhr University Bochum, Bochum, Germany

Artificial intelligence is rapidly advancing, offering powerful tools to automate and enhance various workflows. This research project aims to accelerate the creation of scientific scriptures with the use of Large Language Models (LLM). We use a programming interface (API) to an advanced LLM provided by OpenAI to transform raw lecture material, like audio transcriptions and handwritten notes, into well-phrased and organized formats. In a multi-step process, beginning with the segmentation of the input into distinct topics, the content gets rephrased to enhance readability while ensuring contextual accuracy by addressing any out-of-place terminology. The user can choose the desired output format, such as Markdown or LaTeX, and incorporate images afterwards. While designed for the input of audio transcriptions and notes of hadronphysics lectures, this model could be adapted for any field requiring the transformation of spoken or handwritten content into structured, publication-ready material.

Keywords: Hadronphysics; OpenAI; Lecture Notes; Julia; LLM