Papers by Tobias Hecking
Style Vectors for Steering Generative Large Language Models (2024.findings-eacl)
Copied to clipboard
Kai Konen, Sophie Jentzsch, Diaoulé Diallo, Peer Schütt, Oliver Bensch, Roxanne El Baff, Dominik Opitz, Tobias Hecking
| Challenge: | Large language models (LLMs) can be trained on vast corpora and can generate text in a nuanced and parameterisable way. |
| Approach: | They propose to add style vectors to the activations of hidden layers during text generation to steer output towards specific styles. |
| Outcome: | The proposed approach differs from prompt engineering in that it can be nuanced and parameterisable. |
Corpus Annotation Graph Builder (CAG): An Architectural Framework to Create and Annotate a Multi-source Graph (2023.eacl-demo)
Copied to clipboard
| Challenge: | Graphs are a natural representation of complex data as their structure allows users to discover (often implicit) relations among the nodes intuitively. |
| Approach: | They propose a corpus annotation graph framework that extends graphs with automatically extracted annotations. |
| Outcome: | The proposed framework can be used for further analyses across multiple downstream tasks. |