Authors: Aditya Shrivastava*, Allison Qi*, Callum Canavan*, Tianyi Alex Qiu, Jonathan Michala, Fabien Roger (*Equal contributions, reverse alphabetical) Wen et al. introduced the internal coherence maximization (ICM) algorithm for unsupervised elicitation of base models. They showed that for several datasets, training a base model on labels generated by their algorithm...
The 8th iteration of the Machine Learning Alignment & Theory Scholars (MATS) Program has come to a close, and we want to share the research projects our scholars have been working on this Summer. This cohort had 98 scholars who conducted research with 57 top mentors in the fields of...
Authors: Aditya Shrivastava*, Allison Qi*, Callum Canavan*, Tianyi Alex Qiu, Jonathan Michala, Fabien Roger
(*Equal contributions, reverse alphabetical)
Wen et al. introduced the internal coherence maximization (ICM) algorithm for unsupervised elicitation of base models. They showed that for several datasets, training a base model on labels generated by their algorithm gives similar test accuracy to training on golden labels. To understand which aspects of ICM are most useful, we ran a couple of simple unsupervised elicitation methods that leverage some of the factors that might make ICM work. We compared these baseline methods to training on golden labels for both in-context learning and iterative fine-tuning, using the same datasets as Wen et al. and... (read 2158 more words →)
The 8th iteration of the Machine Learning Alignment & Theory Scholars (MATS) Program has come to a close, and we want to share the research projects our scholars have been working on this Summer. This cohort had 98 scholars who conducted research with 57 top mentors in the fields of AI alignment, transparency, and security.
On Aug 22, we hosted a Program Symposium to showcase their projects to the community; we invited 10 scholar teams to give spotlight talks based on their mid-program Scholar Research Plans, and every scholar contributed to the poster session. You can check out all of the projects in this post!