KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yuan, Fei, Ma, Chang, Yuan, Shuai, Sun, Qiushi, Li, Lei
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909215109414912
author Yuan, Fei
Ma, Chang
Yuan, Shuai
Sun, Qiushi
Li, Lei
author_facet Yuan, Fei
Ma, Chang
Yuan, Shuai
Sun, Qiushi
Li, Lei
contents The lottery ticket hypothesis posits the existence of ``winning tickets'' within a randomly initialized neural network. Do winning tickets exist for LLMs in fine-tuning scenarios? How can we find such winning tickets? In this paper, we propose KS-Lottery, a method to identify a small subset of LLM parameters highly effective in multilingual fine-tuning. Our key idea is to use Kolmogorov-Smirnov Test to analyze the distribution shift of parameters before and after fine-tuning. We further theoretically prove that KS-Lottery can find the certified winning tickets in the embedding layer, fine-tuning on the found parameters is guaranteed to perform as well as full fine-tuning. Comparing KS-Lottery with other parameter-efficient tuning algorithms on translation tasks, the experimental results show that KS-Lottery finds a much smaller set of parameters for fine-tuning while achieving the comparable performance as full fine-tuning LLM. Surprisingly, we find that fine-tuning 18 tokens' embedding of LLaMA suffices to reach the fine-tuning translation performance~\footnote{https://github.com/CONE-MT/KS-Lottery.}.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02801
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models
Yuan, Fei
Ma, Chang
Yuan, Shuai
Sun, Qiushi
Li, Lei
Computation and Language
Artificial Intelligence
Machine Learning
The lottery ticket hypothesis posits the existence of ``winning tickets'' within a randomly initialized neural network. Do winning tickets exist for LLMs in fine-tuning scenarios? How can we find such winning tickets? In this paper, we propose KS-Lottery, a method to identify a small subset of LLM parameters highly effective in multilingual fine-tuning. Our key idea is to use Kolmogorov-Smirnov Test to analyze the distribution shift of parameters before and after fine-tuning. We further theoretically prove that KS-Lottery can find the certified winning tickets in the embedding layer, fine-tuning on the found parameters is guaranteed to perform as well as full fine-tuning. Comparing KS-Lottery with other parameter-efficient tuning algorithms on translation tasks, the experimental results show that KS-Lottery finds a much smaller set of parameters for fine-tuning while achieving the comparable performance as full fine-tuning LLM. Surprisingly, we find that fine-tuning 18 tokens' embedding of LLaMA suffices to reach the fine-tuning translation performance~\footnote{https://github.com/CONE-MT/KS-Lottery.}.
title KS-Lottery: Finding Certified Lottery Tickets for Multilingual Language Models
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2402.02801