Controlling Language and Diffusion Models by Transporting Activations

Controlling Language and Diffusion Models by Transporting Activations

30 October 2024

Luca Zappella

Papers citing "Controlling Language and Diffusion Models by Transporting Activations"

3 / 3 papers shown

Title
SAKE: Steering Activations for Knowledge Editing Marco Scialanga Thibault Laugel Vincent Grari Marcin Detyniecki KELM LLMSV 74 1 0 03 Mar 2025
Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models Anirudh Sundar Sinead Williamson Katherine Metcalf B. Theobald Skyler Seto Masha Fedzechkina LLMSV 80 0 0 24 Feb 2025
Analyze the Neurons, not the Embeddings: Understanding When and Where LLM Representations Align with Humans Masha Fedzechkina Eleonora Gualdoni Sinead Williamson Katherine Metcalf Skyler Seto B. Theobald 43 1 0 20 Feb 2025