4 papers
Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation
Selen Erkan, Bastian Boll, Kristian Kersting +2
Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific formatting requirements. This esp…
A Family of LLMs Liberated from Static Vocabularies
Aleph Alpha, :, Adnen Abdessaied +35
Tokenization is a central component of natural language processing in current large language models (LLMs), enabling models to convert raw text into processable units. Although lea…
Sigma Flows for Image and Data Labeling and Learning Structured Prediction
Jonas Cassel, Bastian Boll, Stefania Petra +2
This paper introduces the sigma flow model for the prediction of structured labelings of data observed on Riemannian manifolds, including Euclidean image domains as special case. T…
Generative Assignment Flows for Representing and Learning Joint Distributions of Discrete Data
Bastian Boll, Daniel Gonzalez-Alvarado, Stefania Petra +1
We introduce a novel generative model for the representation of joint probability distributions of a possibly large number of discrete random variables. The approach uses measure t…