1 code implementation • Automated Knowledge Base Construction 2022 • Jan-Christoph Kalo, Leandra Fichtel
Instead of performing the evaluation on masked language models, we present results for a variety of recent causal LMs in a few-shot setting.
Ranked #1 on Probing Language Models on KAMEL
1 code implementation • AKBC 2021 • Leandra Fichtel, Jan-Christoph Kalo, Wolf-Tilo Balke
In this work, we propose using a completely different approach: Instead of spending resources on training an additional model, we simply perform an adaptive fine-tuning of the pre-trained language model on the standard fill-mask task using a small training dataset of existing facts from a knowledge graph.