12 papers
Embracing the Enemy
Ãlvaro Delgado-Vega, Álvaro Delgado-Vega, Johannes Schneider
A principal can partially influence the allocation of power between two competing parties. The principal is closer to one party, the ``friend'', than to the other, the ``enemy''. T…
Topic Modeling with Fine-tuning LLMs and Bag of Sentences
Johannes Schneider
Large language models (LLMs) are increasingly used for topic modeling, outperforming classical topic models such as LDA. Commonly, pre-trained LLM encoders such as BERT are used ou…
Causally Reliable Concept Bottleneck Models
Giovanni De Felice, Arianna Casanova Flores, Francesco De Santis +4
Concept-based models are an emerging paradigm in deep learning that constrains the inference process to operate through human-interpretable variables, facilitating explainability a…
Focus on Likely Classes for Test-Time Prediction
Johannes Schneider
We ask: Can focusing on likely classes of a single, in-domain sample improve model predictions? Prior work argued ``no''. We put forward a novel rationale in favor of ``yes'': Shar…
Empowering Clients -- Transformation of Design Processes Due to Generative AI
Johannes Schneider, Kilic Sinem, Daniel Stockhammer
Generative AI (GenAI) is transforming creative fields shaping our culture and our heritage. We focus on widespread interactions between clients and (creative) specialists highlight…
Mapping the Landscape of Open Access Dashboards -- A Dataset for Research and Infrastructure Development
Johannes Schneider, Heinz Pampel
As Open Access continues to gain importance in science policy, understanding the proportion of Open Access publications relative to the total research output of research-performing…