Search Results for author: Mark Rofin

Found 3 papers, 2 papers with code

Why are Sensitive Functions Hard for Transformers?

1 code implementation15 Feb 2024 Michael Hahn, Mark Rofin

We show theoretically and empirically that this theory unifies a broad array of empirical observations about the learning abilities and biases of transformers, such as their generalization bias towards low sensitivity and low degree, and difficulty in length generalization for PARITY.

Linear Interpolation In Parameter Space is Good Enough for Fine-Tuned Language Models

no code implementations22 Nov 2022 Mark Rofin, Nikita Balagansky, Daniil Gavrilov

The simplest way to obtain continuous interpolation between two points in high dimensional space is to draw a line between them.

Attribute Text Generation

Vote'n'Rank: Revision of Benchmarking with Social Choice Theory

1 code implementation11 Oct 2022 Mark Rofin, Vladislav Mikhailov, Mikhail Florinskiy, Andrey Kravchenko, Elena Tutubalina, Tatiana Shavrina, Daniel Karabekyan, Ekaterina Artemova

The development of state-of-the-art systems in different applied areas of machine learning (ML) is driven by benchmarks, which have shaped the paradigm of evaluating generalisation capabilities from multiple perspectives.

Benchmarking Result aggregation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.