Master's thesis at Fraunhofer: key facts
- Opportunity type
- Master's thesis
- Organization
- Fraunhofer
- Location
- Darmstadt, Germany
- Field / discipline
- Technology and Software
- Application deadline
- Deadline not specified — apply early
- Last source check
- 20 Nov 2026
About this master's thesis at Fraunhofer
Background and Motivation
Parameter-efficient fine-tuning (PEFT) adapters are an excellent tool for adding new capabilities to LLMs with only a small number of parameters. Thanks to their reduced capacity, adapters are lightweight and therefore quick to train and distribute, while still achieving performance comparable to full fine-tuning. Methods from mechanistic interpretability make it possible to identify specific parameters in LLMs that are responsible for particular capabilities of the network, such as alignment. The goal of this thesis is to deactivate these safety parameters in the final model in a targeted way using PEFT adapters, thereby removing the alignment.
Goal
The challenge is that, due to the lower capacity of the adapters, parameters can no longer be masked in a targeted way. The goal is therefore to steer the adapters so that a large share of the safety neurons is still modified and the alignment is effectively bypassed.
Results
The intended result of the thesis is a comparison of the effectiveness of adapters with different capacities and methods. In addition to a proof of concept, the thesis will examine which adapter configuration is most vulnerable to such an attack.
Note
For a bachelor’s thesis, the scope can be reduced by considering only LoRA adapters.
Be part of change
Research and implement novel machine learning approaches that improve the safety of LLMs
Critically evaluate your results
Present your results
Write a project report in the form of a thesis
Before you apply
0 of 4 readyA preparation checklist, saved in this browser on this device without an account. It does not sync across devices. The official posting determines eligibility and required documents.
How to apply
Apply via jobs.fraunhofer.de. Check the original listing for required documents and submission instructions.
Source and listing information
Application source: jobs.fraunhofer.de. Listing details may change; confirm them on the source site. A source check confirms page availability, not endorsement of the organization.
Report an outdated or incorrect listing