Abstract:
Educational materials, political discourse, and online communities do more than communicate information: they express perspectives, values, and worldviews. In our information ecosystem, these human representations are no longer only interpreted by people – they are also learned, reproduced, and transformed by AI systems.
This talk explores the connections between framing, pluralism, and AI alignment through the lens of representation. What does it mean for an AI system to represent a perspective? Can models capture diverse viewpoints without collapsing them into a single “average” position? And how should we think about alignment when values themselves are heterogeneous and contested?
Lucie Flek argues that many AI alignment challenges boil down to challenges of representation: whose perspectives are captured, which values are privileged, and whether our evaluation methods are even robust enough to evaluate and control these choices.

Speaker’s bio:
Lucie Flek is a full professor at the University of Bonn, leading the Data Science and Language Technologies group. Her main interests lie in machine learning research for natural language processing (NLP), including AI robustness and safety. The application areas range from large language models and conversational systems, across clinical NLP and mental health research, to misinformation detection and social media analyses. Prof. Flek has been active both in academia and industry – she used to manage natural language understanding research programs in Amazon Alexa and contributed to the Google Shopping Search launch in Europe. Her academic work at the University of Pennsylvania and University College London revolved around user modeling from text, and its applications in psychology and social sciences. Her PhD at TU Darmstadt focused on meaning ambiguity, incorporating expert lexical-semantic resources into DNN classification tasks. She has served as Area Chair for Computational Social Sciences at numerous ACL* conferences, and as an editor of the NLP section of multiple AI journals. Before her career path in natural language processing, Prof. Flek has been contributing to particle physics research at CERN in the area of axion searches.