Cite
Notes
Only stored in your browser.
Attribution
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
arXiv 2025
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
arXiv 2024
from 2 papers
Andrew Lee
Martin Wattenberg
Xiaoyan Bai
Chenhao Tan
Fernanda Viégas
Jonathan K. Kummerfeld
Rada Mihalcea
Stuart Shieber
Yuntian Deng
professor