Saved in:
Bibliographic Details
Main Authors: Naim, Omar, Bolte, Jerome, Asher, Nicholas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.03503
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915603281870848
author Naim, Omar
Bolte, Jerome
Asher, Nicholas
author_facet Naim, Omar
Bolte, Jerome
Asher, Nicholas
contents Our paper challenges claims from prior research that transformer-based models, when learning in context, implicitly implement standard learning algorithms. We present empirical evidence inconsistent with this view and provide a mathematical analysis demonstrating that transformers cannot achieve general predictive accuracy due to inherent architectural limitations.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03503
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Analyzing limits for in-context learning
Naim, Omar
Bolte, Jerome
Asher, Nicholas
Machine Learning
Artificial Intelligence
Our paper challenges claims from prior research that transformer-based models, when learning in context, implicitly implement standard learning algorithms. We present empirical evidence inconsistent with this view and provide a mathematical analysis demonstrating that transformers cannot achieve general predictive accuracy due to inherent architectural limitations.
title Analyzing limits for in-context learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.03503