## Active PHD Students - Betiel Woldai: Evaluating the Alignment of Large Language Models: An integrative perspective - Sophie Henne: BIAS Detection in Data - Sandra Nuißl: Evaluation metrics for translations - Wanwei Lin: Multi-agents for optimizing automation in supply chain management - Fabian Maag: AI Alignment & Mechanistic Interpretability - Sudarshan Kamath Barkur: AI Safety with a focus on LLMs (building pattern DB) ## Active M.S. (Thesis) - Tamina Unger (KDT): NLP in der Medizin und der Einflussfaktor "Adversarial Attacks" - ein Literature Review - Sven Leuschner (KDT): Evaluation von RAG Systemen ohne manuellen Goldstandard - Max Magerstädt (Aalen): Kontinuierliche Drift Erkennung in Sprachmodellen - Hien Nguyen (Aalen): Enhancing Human likeness in Speech to Text synthesis - Marcel Caballero (Aalen): AGI ## Former M.S. (Thesis) - Melanie Köppel (2024): Real-Time Automatic Speech Recognition for Semi-Automatic Labeling of Used Textiles: Ecaluation of Adaptive Approaches for End-to-End ASR Systems - Leo Donisch (2024): Unlocking the Efficiency of Language Models: Balancing Efficiency and Quality in Instruction-Tuned Models - Roman Aperdannier (2024): Structured evaluation of common machine learning and deep learning methods for online speaker diarization including the development of optimization approaches for the best performing method. ## Transfer projects - Simon Steinbach (2024): Quality Improvements with Optical Failure Detection. - [[@Julia Riehle]] (2024): Classification of incoming eMails