Papers with *Stochastic Tuning*

1 papers
Stochastic Fine-Tuning of Language Models Using Masked Gradients (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are the dominant paradigm in Natural Language Processing but fine-tuning them for specific downstream tasks often requires updating a vast number of parameters.
Approach: They propose a method that selectively updates a small subset of parameters in each step of the tuning process.
Outcome: The proposed approach outperforms existing fine-tuning methods while updating merely **0.08**% of the model’s parameters.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations