Papers by Tobias Hecking

2 papers
Style Vectors for Steering Generative Large Language Models (2024.findings-eacl)

Copied to clipboard

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations