Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning

MATS Fellow:

Boyd Kane, Jo Jiao, Elizabeth Donoway, Alex Cloud

Authors:

Citations

Citations

Abstract:

Recent research

Gradient Routing Localizes and Removes Unintended Behaviors in RL

Authors:

Jake Ward, Shawn Hu, Aria Wong, Nathan Hu, Alex Cloud

Date:

December 9, 2026

Citations:

Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning

Authors:

Boyd Kane, Jo Jiao, Elizabeth Donoway, Alex Cloud

Date:

December 8, 2026

Citations:

Frequently asked questions

What is the MATS Program?
How long does the program last?