MATS Alumnus
Constantin Venhoff
Collabortators
Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda
Citations
Abstract
Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance, controlling their reasoning processes remains challenging. This work presents a steering approach for thinking LLMs by analyzing and manipulating specific reasoning behaviors in DeepSeek-R1-Distill models. Through a systematic experiment on 500 tasks across 10 diverse categories, we identify several reasoning behaviors exhibited by thinking models, including expressing uncertainty, generating examples for hypothesis validation, and backtracking in reasoning chains. We demonstrate that these behaviors are mediated by linear directions in the model's activation space and can be controlled using steering vectors. By extracting and applying these vectors, we provide a method to modulate specific aspects of the model's reasoning process, such as its tendency to backtrack or express uncertainty. Our approach offers practical tools for steering reasoning processes in thinking models in a controlled and interpretable manner. We validate our steering method using three DeepSeek-R1-Distill models, demonstrating consistent control across different model architectures.
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
Authors:
Jorio Cocola, Dylan Feng
Date:
December 10, 2025
Citations:
0
AI agents find $4.6M in blockchain smart contract exploits
Authors:
Fellow: Winnie Xiao
Date:
December 1, 2025
Citations:
0
The MATS Program is an independent research and educational initiative connecting emerging researchers with mentors in AI alignment, governance, and security.
Each MATS cohort runs for 12 weeks in Berkeley, California, followed by an optional 6–12 month extension in London for selected scholars.