Elastic Architecture Search for Efficient Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Wang, Shang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917052537634816
author Wang, Shang
author_facet Wang, Shang
contents As large pre-trained language models become increasingly critical to natural language understanding (NLU) tasks, their substantial computational and memory requirements have raised significant economic and environmental concerns. Addressing these challenges, this paper introduces the Elastic Language Model (ELM), a novel neural architecture search (NAS) method optimized for compact language models. ELM extends existing NAS approaches by introducing a flexible search space with efficient transformer blocks and dynamic modules for dimension and head number adjustment. These innovations enhance the efficiency and flexibility of the search process, which facilitates more thorough and effective exploration of model architectures. We also introduce novel knowledge distillation losses that preserve the unique characteristics of each block, in order to improve the discrimination between architectural choices during the search process. Experiments on masked language modeling and causal language modeling tasks demonstrate that models discovered by ELM significantly outperform existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27037
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Elastic Architecture Search for Efficient Language Models
Wang, Shang
Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
As large pre-trained language models become increasingly critical to natural language understanding (NLU) tasks, their substantial computational and memory requirements have raised significant economic and environmental concerns. Addressing these challenges, this paper introduces the Elastic Language Model (ELM), a novel neural architecture search (NAS) method optimized for compact language models. ELM extends existing NAS approaches by introducing a flexible search space with efficient transformer blocks and dynamic modules for dimension and head number adjustment. These innovations enhance the efficiency and flexibility of the search process, which facilitates more thorough and effective exploration of model architectures. We also introduce novel knowledge distillation losses that preserve the unique characteristics of each block, in order to improve the discrimination between architectural choices during the search process. Experiments on masked language modeling and causal language modeling tasks demonstrate that models discovered by ELM significantly outperform existing methods.
title Elastic Architecture Search for Efficient Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2510.27037