Gradient Transformer: Learning to Generate Updates for LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Binh-Nguyen, Tran, Khang, Phan, NhatHai, Khalil, Issa
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916052475052032
author Nguyen, Binh-Nguyen
Tran, Khang
Phan, NhatHai
Khalil, Issa
author_facet Nguyen, Binh-Nguyen
Tran, Khang
Phan, NhatHai
Khalil, Issa
contents Many organizations lack computational resources to fine-tune large language models (LLMs) on private (unshareable) data for better utility, while fine-tuning tiny language models (TinyLMs) alone performs poorly. To address this bottleneck, we propose a data-free knowledge distillation framework that generates LLM update vectors based on TinyLMs fine-tuned on private data. An update vector is a vector of parameter changes from an initial model to its fine-tuned version on a dataset, capturing the effect of cumulative gradient steps during fine-tuning. The key idea of our framework is a novel Gradient Transformer that transforms TinyLM's update vectors into LLM's update vectors. As derived from shadow datasets, Grad-Transformer captures the correlation between TinyLM and LLM update vectors, enabling third-party providers to generate LLM update vectors given the organization's TinyLM update vectors without accessing the organization's private data. The framework supports multi-organization collaboration to jointly update LLMs, improving performance and cost-efficiency. Extensive experiments across language modeling and reasoning tasks show that Grad-Transformer remarkably outperforms state-of-the-art knowledge distillation baselines, even under strict differential privacy protection.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27591
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gradient Transformer: Learning to Generate Updates for LLMs
Nguyen, Binh-Nguyen
Tran, Khang
Phan, NhatHai
Khalil, Issa
Machine Learning
Many organizations lack computational resources to fine-tune large language models (LLMs) on private (unshareable) data for better utility, while fine-tuning tiny language models (TinyLMs) alone performs poorly. To address this bottleneck, we propose a data-free knowledge distillation framework that generates LLM update vectors based on TinyLMs fine-tuned on private data. An update vector is a vector of parameter changes from an initial model to its fine-tuned version on a dataset, capturing the effect of cumulative gradient steps during fine-tuning. The key idea of our framework is a novel Gradient Transformer that transforms TinyLM's update vectors into LLM's update vectors. As derived from shadow datasets, Grad-Transformer captures the correlation between TinyLM and LLM update vectors, enabling third-party providers to generate LLM update vectors given the organization's TinyLM update vectors without accessing the organization's private data. The framework supports multi-organization collaboration to jointly update LLMs, improving performance and cost-efficiency. Extensive experiments across language modeling and reasoning tasks show that Grad-Transformer remarkably outperforms state-of-the-art knowledge distillation baselines, even under strict differential privacy protection.
title Gradient Transformer: Learning to Generate Updates for LLMs
topic Machine Learning
url https://arxiv.org/abs/2605.27591