Home // Determinantal Point Processes for Prompt Engineering for LLMs
Type of thesis: Masterarbeit / location: Dresden / Status of thesis: Open theses
The performance of a large language model (LLM) is sensitive to the way it is prompted. Automated prompt engineering methods aim to find suitable prompts for a given task by sampling several prompts and evaluating them. Existing automatic prompt engineering methods do not generate sufficiently diverse sample prompts or rely on several meta-prompting tricks to achieve the desired results. In this thesis, we will use a method for prompt selection to directly optimise diversity and estimated performance by exploiting so called determinental point processes. The thesis will involve comparisons of this technique to state-of-the-art prompt engineering methods such as PromptBreeder from DeepMind.
TU Dresden
Nature-Inspired Machine Intelligence
ScaDS.AI Dresden/Leipzig (Center for Scalable Data Analytics and Artificial Intelligence) is a center for Data Science, Artificial Intelligence and Big Data with locations in Dresden and Leipzig.
Technische Universität Dresden ScaDS.AI Dresden/Leipzig Bürogebäude Strehlener Straße Strehlener Straße 12, 14 01069 Dresden
Löhrs Carré Humboldtstraße 25, 3. Obergeschoss 04105 Leipzig Postal address Leipzig: Universität Leipzig Data Science Zentrum Internes Postfach: 212104 04081 Leipzig
Copyright 2024 © ScaDS.AI Dresden/Leipzig – All rights reserved.