4 papers
What do your logits know? (The answer may surprise you!)
Masha Fedzechkina, Eleonora Gualdoni, Rita Ramos +1
Recent work has shown that probing model internals can reveal a wealth of information not apparent from the model generations. This poses the risk of unintentional or malicious inf…
ExpertLens: Activation steering features are highly interpretable
Masha Fedzechkina, Eleonora Gualdoni, Sinead Williamson +3
Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amoun…
Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
Anirudh Sundar, Sinead Williamson, Katherine Metcalf +3
Aligned representations across languages is a desired property in multilingual large language models (mLLMs), as alignment can improve performance in cross-lingual tasks. Typically…
Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions
Eray Erturk, Fahad Kamran, Salar Abbaspourazad +6
Wearable devices record physiological and behavioral signals that can improve health predictions. While foundation models are increasingly used for such predictions, they have been…