5 papers
Robust Generalizable Heterogeneous Legal Link Prediction
Lorenz Wendlinger, Simon Alexander Nonn, Abdullah Al Zubaer +1
Recent work has applied link prediction to large heterogeneous legal citation networks \new{with rich meta-features}. We find that this approach can be improved by including edge d…
On the Suitability of pre-trained foundational LLMs for Analysis in German Legal Education
Lorenz Wendlinger, Christian Braun, Abdullah Al Zubaer +4
We show that current open-source foundational LLMs possess instruction capability and German legal background knowledge that is sufficient for some legal analysis in an educational…
Enhancing Rhetorical Figure Annotation: An Ontology-Based Web Application with RAG Integration
Ramona Kühn, Jelena Mitrović, Michael Granitzer
Rhetorical figures play an important role in our communication. They are used to convey subtle, implicit meaning, or to emphasize statements. We notice them in hate speech, fake ne…
Krony-PT: GPT2 compressed with Kronecker Products
Mohamed Ayoub Ben Ayad, Jelena Mitrovic, Michael Granitzer
We introduce Krony-PT, a compression technique for GPT-2 based on Kronecker products. We specifically target the feed-forward weights of each transformer block, and systematically…
Towards an Improved Metric for Evaluating Disentangled Representations
Sahib Julka, Yashu Wang, Michael Granitzer
Disentangled representation learning plays a pivotal role in making representations controllable, interpretable and transferable. Despite its significance in the domain, the quest…