3 papers
cs.CL2026
Tracing Persona Vectors Through LLM Pretraining
Viktor Moskvoretskii, Dominik Glandorf, Jorge Medina Moreira +2
How large language models internally represent high-level behaviors is a core interpretability question with direct relevance to AI safety: it determines what we can detect, audit,…
cs.CL2025
SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling
Fares Fawzi, Vinitra Swamy, Dominik Glandorf +2
Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concer…
cs.LG2025
Intrinsic User-Centric Interpretability through Global Mixture of Experts
Vinitra Swamy, Syrielle Montariol, Julian Blackwell +3
In human-centric settings like education or healthcare, model accuracy and model explainability are key factors for user adoption. Towards these two goals, intrinsically interpreta…