2026 COLM Towards Isolated Interventions via Almost Orthogonal Features in Language Models Moritz Miller, Florent Draye, and Bernhard Schölkopf 2026 arXiv ACL On the Emergence and Test-Time Use of Structural Information in Large Language Models Michelle Chao Chen, Moritz Miller, Bernhard Schölkopf, and 1 more author 2026 arXiv 2025 NeurIPS Counterfactual Reasoning: An Analysis of In-Context Emergence Moritz Miller, Bernhard Schölkopf, and Siyuan Guo In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025 arXiv ACL Findings First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning Kushal Jain, Moritz Miller, Niket Tandon, and 1 more author In The 63rd Annual Meeting of the Association for Computational Linguistics, 2025 arXiv