Magdalena Theresa Kaiser after successfully defending her thesis. Photo: MPI-INF/Bertram Somieski
On Wednesday, 04 February 2026, Magdalena Theresa Kaiser defended her thesis with the title: "Reinforcement Learning from Implicit Feedback for Conversational Question Answering". She was a PhD researcher from June 2019 until December 2025 under the supervision of Prof. Gerhard Weikum, head of Department "Databases and Information Systems", and Dr. Rishiraj Saha Roy. The doctoral degree is awarded by Saarland University.
Abstract of the thesis:
Conversational systems that enable interactions with users in natural language to satisfy their information needs and assist them in completing their tasks have been a long-standing goal. Recent advancements in Machine Learning and Natural Language Processing have enabled the development of such systems. Feedback is essential to continuously improve and adapt these systems to users’ needs. This thesis focuses on Conversational Question Answering (ConvQA), where the task is to provide crisp answers to fact-centric questions, formulated in natural language.
ConvQA models are usually trained and evaluated on benchmarks of gold-standard question-answer pairs. Manually judging answer correctness is costly and therefore often not available in real-world scenarios. If available, these judgments are often limited in scope and quality. This thesis studies forms of implicit feedback to effectively train and improve conversational systems from limited amounts of data.