5 papers
Verbalized and Internal Probabilities Are Coupled in Large Language Models
Sinead Williamson, Jiaxuan Li, Nick Foti +2
Large language models carry an internal notion of uncertainty in their sampling distribution, i.e., the probabilities they place on generating one answer rather than another. They…
What do your logits know?
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 a risk of unintentional or malicious infor…
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…
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…
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…