Salvato in:
Dettagli Bibliografici
Autori principali: Wilcoxson, Max, Svendgård, Morten, Doshi, Ria, Davis, Dylan, Vir, Reya, Sahai, Anant
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2407.19346
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929439100633088
author Wilcoxson, Max
Svendgård, Morten
Doshi, Ria
Davis, Dylan
Vir, Reya
Sahai, Anant
author_facet Wilcoxson, Max
Svendgård, Morten
Doshi, Ria
Davis, Dylan
Vir, Reya
Sahai, Anant
contents Simple function classes have emerged as toy problems to better understand in-context-learning in transformer-based architectures used for large language models. But previously proposed simple function classes like linear regression or multi-layer-perceptrons lack the structure required to explore things like prompting and alignment within models capable of in-context-learning. We propose univariate polynomial regression as a function class that is just rich enough to study prompting and alignment, while allowing us to visualize and understand what is going on clearly.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19346
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Polynomial Regression as a Task for Understanding In-context Learning Through Finetuning and Alignment
Wilcoxson, Max
Svendgård, Morten
Doshi, Ria
Davis, Dylan
Vir, Reya
Sahai, Anant
Machine Learning
Computation and Language
Simple function classes have emerged as toy problems to better understand in-context-learning in transformer-based architectures used for large language models. But previously proposed simple function classes like linear regression or multi-layer-perceptrons lack the structure required to explore things like prompting and alignment within models capable of in-context-learning. We propose univariate polynomial regression as a function class that is just rich enough to study prompting and alignment, while allowing us to visualize and understand what is going on clearly.
title Polynomial Regression as a Task for Understanding In-context Learning Through Finetuning and Alignment
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2407.19346