Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls
Paper
•
2510.00184
•
Published
•
16
Itamar Pres
ipres
AI & ML interests
None yet
Recent Activity
authored
a paper
17 days ago
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO
and Toxicity
authored
a paper
17 days ago
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals
Long-Range Dependency Pitfalls
Organizations
None yet
upvoted
a
paper
18 days ago