Login / Signup
Itamar Pres
Publication Activity (10 Years)
Years Active: 2024-2024
Publications (10 Years): 1
Top Topics
Data Mining Algorithms
Machine Learning Algorithms
Orders Of Magnitude
Top Venues
CoRR
</>
Publications
</>
Andrew Lee
,
Xiaoyan Bai
,
Itamar Pres
,
Martin Wattenberg
,
Jonathan K. Kummerfeld
,
Rada Mihalcea
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
CoRR
(2024)