Room FW26 with Hybrid Format. Here is the Zoom link for those that wish to join online: https://cam-ac-uk.zoom.us/j/4751389294?pwd=Z2ZOSDk0eG1wZldVWG1GVVhrTzFIZz09


2025-05-02 12:00: Asymmetry in Supposedly Equivalent Facts: Pre-training Bias in Large Language Models (Zifeng Ding (University of Cambridge))

2025-05-09 12:00: Research Progress in Mechanistic Interpretability (Arthur Conmy (Google DeepMind))

2025-05-16 12:00: Measuring Political Bias in Large Language Models (Paul Röttger (Bocconi University))

2025-05-30 12:00: Unveiling the Secret Sauce: A Causal Look at Data Memorisation and Tokenisation in Language Models (Pietro Lesci (University of Cambridge))