Picture for Niklas Stoehr

Niklas Stoehr

Activation Scaling for Steering and Interpreting Language Models

Add code
Oct 07, 2024
Viaarxiv icon

Context versus Prior Knowledge in Language Models

Add code
Apr 06, 2024
Viaarxiv icon

Localizing Paragraph Memorization in Language Models

Add code
Mar 28, 2024
Viaarxiv icon

Unsupervised Contrast-Consistent Ranking with Language Models

Add code
Sep 13, 2023
Viaarxiv icon

ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task

Add code
Jul 12, 2023
Figure 1 for ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task
Figure 2 for ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task
Figure 3 for ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task
Figure 4 for ACTI at EVALITA 2023: Overview of the Conspiracy Theory Identification Task
Viaarxiv icon

Generalizing Backpropagation for Gradient-Based Interpretability

Add code
Jul 06, 2023
Viaarxiv icon

World Models for Math Story Problems

Add code
Jun 07, 2023
Viaarxiv icon

Extracting Victim Counts from Text

Add code
Feb 23, 2023
Viaarxiv icon

The Ordered Matrix Dirichlet for Modeling Ordinal Dynamics

Add code
Dec 08, 2022
Viaarxiv icon

Extended Multilingual Protest News Detection -- Shared Task 1, CASE 2021 and 2022

Add code
Nov 21, 2022
Viaarxiv icon