Narmeen developed, ideated and validated K-steering at Martian. Luke generated the baselines, figures and wrote this blog post. Amir proposed the research direction and supervised the project. The full interactive blog will be available closer to the publication of the complete paper on the Martian website. TL;DR: We introduce K-steering,...
by Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash, Amirali Abdullah This work was done by Narmeen Oozeer as a research fellow at Martian, under an AI safety grant supervised by PIs Amirali Abdullah and Dhruv Nathawani. Special thanks to Sasha Hydrie, Chaithanya Bandi and Shriyash Upadhyay at Martian for suggesting researching...
Narmeen developed, ideated and validated K-steering at Martian. Luke generated the baselines, figures and wrote this blog post. Amir proposed the research direction and supervised the project. The full interactive blog will be available closer to the publication of the complete paper on the Martian website.
TL;DR: We introduce K-steering, a steering method for language models that allows for steering in multiple simultaneous directions. Our preliminary results show it outperforms a contrastive activation addition (CAA) baseline.
We introduce K-Steering, a method for steering language models in multiple directions simultaneously by perturbing activations according to the logits of a multilabel classifier. We experiment with steering conversational tone, showing that K-steering can cause a classifier to... (read 1807 more words →)
by Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash, Amirali Abdullah
This work was done by Narmeen Oozeer as a research fellow at Martian, under an AI safety grant supervised by PIs Amirali Abdullah and Dhruv Nathawani. Special thanks to Sasha Hydrie, Chaithanya Bandi and Shriyash Upadhyay at Martian for suggesting researching generalized backdoor mitigations as well as extensive logistical support and helpful discussions.
TLDR: