Can Gradient Descent Simulate Prompting?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Eric, Choshen, Leshem, Andreas, Jacob
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913913072779264
author Zhang, Eric
Choshen, Leshem
Andreas, Jacob
author_facet Zhang, Eric
Choshen, Leshem
Andreas, Jacob
contents There are two primary ways of incorporating new information into a language model (LM): changing its prompt or changing its parameters, e.g. via fine-tuning. Parameter updates incur no long-term storage cost for model changes. However, for many model updates, prompting is significantly more effective: prompted models can generalize robustly from single examples and draw logical inferences that do not occur under standard fine-tuning. Can models be modified so that fine-tuning does emulate prompting? This paper describes a method for meta-training LMs such that gradient updates emulate the effects of conditioning on new information. Our approach uses tools from gradient-based meta-learning but uses an LM's own prompted predictions as targets, eliminating the need for ground-truth labels. Subsequent gradient descent training recovers some (and occasionally all) of prompted model performance -- showing improvement on the ``reversal curse'' tasks, and answering questions about text passages after a single gradient update. These results suggest that, with appropriate initialization, gradient descent can be surprisingly expressive. Our results suggest new avenues for long-context modeling and offer insight into the generalization capabilities of gradient-based learning.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20989
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can Gradient Descent Simulate Prompting?
Zhang, Eric
Choshen, Leshem
Andreas, Jacob
Computation and Language
Machine Learning
There are two primary ways of incorporating new information into a language model (LM): changing its prompt or changing its parameters, e.g. via fine-tuning. Parameter updates incur no long-term storage cost for model changes. However, for many model updates, prompting is significantly more effective: prompted models can generalize robustly from single examples and draw logical inferences that do not occur under standard fine-tuning. Can models be modified so that fine-tuning does emulate prompting? This paper describes a method for meta-training LMs such that gradient updates emulate the effects of conditioning on new information. Our approach uses tools from gradient-based meta-learning but uses an LM's own prompted predictions as targets, eliminating the need for ground-truth labels. Subsequent gradient descent training recovers some (and occasionally all) of prompted model performance -- showing improvement on the ``reversal curse'' tasks, and answering questions about text passages after a single gradient update. These results suggest that, with appropriate initialization, gradient descent can be surprisingly expressive. Our results suggest new avenues for long-context modeling and offer insight into the generalization capabilities of gradient-based learning.
title Can Gradient Descent Simulate Prompting?
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2506.20989