Author

Dmitrii Troitskii

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

The First Few Tokens Matter: Understanding Chain-of-Thought Controllability

This work investigates the source of an entropy collapse in the first few tokens following the opening thinking tag and exploits this mechanism to recover CoT controllability through two inference-time interventions on initial tokens, finding that the relationship with monitorability depends on the evaluation.

Hugh Van Deventer, Dmitrii Troitskii, L. Ruis · 0 citations

#artificial intelligence Preprint Sep 2026

Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds

Two techniques that make simulated alignment evaluations harder to distinguish from real deployments are presented, and automated approaches can improve the realism of alignment evaluations, and that these improvements use additional compute more effectively than making the audits longer.

Axel Ahlqvist, Richard Guan, Juan-Pablo Rivera et al. · 0 citations