profile picture

Lucie Flek

personalization

perspectivism

question answering

fairness

reasoning

large language models

user modeling

narrative

entropy

real-world noise

sentence similarity

perplexity

human-centered nlp

evidence extraction

suicide risk

8

presentations

3

number of views

SHORT BIO

Professor Dr. Lucie Flek conducts research at the University of Bonn and University of Marburg, leading the research group on Conversational AI and Social Analytics (CAISA). Her research combines insights from the fields of machine learning, natural language processing, computational social sciences, and human-machine interaction. The focus of her current investigations is the development of machine learning systems with the incorporating the individual language use of different people and sociodemographic groups. In this way, Professor Flek hopes to make personalized AI systems useful to a wide audience. In her earlier academic work at TU Darmstadt, Positive Psychology Center at University of Pennsylvania, and University College London, she has been focusing on psychological and social applications of stylistic variation insights. She regularly serves as Area Chair for Computational Social Sciences. Previously, she has worked on data science at the European Organization for Nuclear Research (CERN), Google, and Amazon Alexa AI.

Presentations

Can Stories Help LLMs Reason? Curating Information Space Through Narrative

Vahid Sadiri Javadi and 2 other authors

Exploring Robustness of Multilingual LLMs on Real-World Noisy Data

Amirhossein Aliakbarzadeh and 1 other author

Perspective Taking through Generating Responses to Conflict Situations

Joan Plepi and 2 other authors

Harnessing Personalization Methods to Identify and Predict Unreliable Information Spreader Behavior

Shaina Ashraf and 3 other authors

Corpus Considerations for Annotator Modeling and Scaling

Sarumi Olufunke Oluyemi and 5 other authors

The Impact of Differential Privacy on Group Disparity Mitigation

Victor Hansen and 4 other authors

Archetypes and Entropy: Theory-Driven Extraction of Evidence for Suicide Risk

Vasudha Varadarajan and 13 other authors

Unifying Data Perspectivism and Personalization: An Application to Social Norms

Lucie Flek and 3 other authors

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Presentations
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2025 Underline - All rights reserved