Schut, Lisa

8 publications

ICLRW 2025 Do Multilingual LLMs Think in English? Lisa Schut, Yarin Gal, Sebastian Farquhar

TMLR 2025 Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors Angus Nicolson, Lisa Schut, Alison Noble, Yarin Gal

UAI 2025 Hindsight Merging: Diverse Data Generation with Language Models Veniamin Veselovsky, Benedikt Stroebl, Gianluca Bencomo, Dilip Arumugam, Lisa Schut, Arvind Narayanan, Thomas L. Griffiths

ICMLW 2024 Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs Jiatong Han, Jannik Kossen, Muhammed Razzak, Lisa Schut, Shreshth A Malik, Yarin Gal

AISTATS 2021 Generating Interpretable Counterfactual Explanations by Implicit Minimisation of Epistemic and Aleatoric Uncertainties Lisa Schut, Oscar Key, Rory Mc Grath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal

NeurIPSW 2021 DeDUCE: Generating Counterfactual Explanations at Scale Benedikt Höltgen, Lisa Schut, Jan M. Brauner, Yarin Gal

NeurIPS 2021 Speedy Performance Estimation for Neural Architecture Search Robin Ru, Clare Lyle, Lisa Schut, Miroslav Fil, Mark van der Wilk, Yarin Gal

NeurIPS 2020 A Bayesian Perspective on Training Speed and Model Selection Clare Lyle, Lisa Schut, Robin Ru, Yarin Gal, Mark van der Wilk