3 papers
cs.LG2025
Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers
Tobias Leemann, Alina Fastowski, Felix Pfeiffer +1
We address the critical challenge of applying feature attribution methods to the transformer architecture, which dominates current applications in natural language processing and b…
cs.AI2024
Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
Yao Rong, Tobias Leemann, Thai-trang Nguyen +6
Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A better understanding of the needs of XAI users, as well as human-centered evaluations of e…
cs.CL2024
The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI
Miriam Schirmer, Tobias Leemann, Gjergji Kasneci +2
Psychological trauma can manifest following various distressing events and is captured in diverse online contexts. However, studies traditionally focus on a single aspect of trauma…