3 papers
cs.CR2026
Basic Legibility Protocols Improve Trusted Monitoring
Ashwin Sreevatsa, Sebastian Prasanna, Cody Rushing
The AI Control research agenda aims to develop control protocols: safety techniques that prevent untrusted AI systems from taking harmful actions during deployment. Because human o…
cs.CR2025
Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
Yeonwoo Jang, Shariqah Hossain, Ashwin Sreevatsa +1
In this work, we demonstrate that certain machine unlearning methods may fail under straightforward prompt attacks. We systematically evaluate eight unlearning techniques across th…
cs.CL2021
DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation
Xinyu Hua, Ashwin Sreevatsa, Lu Wang
We study the task of long-form opinion text generation, which faces at least two distinct challenges. First, existing neural generation models fall short of coherence, thus requiri…