Marks, Luke

2 publications

ICLR 2026 Output Supervision Can Obfuscate the Chain of Thought Jacob Drori, Luke Marks, Bryce Woodworth, Alex Cloud, Alexander Matt Turner

NeurIPS 2024 Interpreting Learned Feedback Patterns in Large Language Models Luke Marks, Amir Abdullah, Clement Neo, Rauno Arike, David Krueger, Philip Torr, Fazl Barez