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. Code and model will be released to the public.

翻译：彩票假设认为，在随机初始化的神经网络中存在"中奖票"。在微调场景下，大语言模型中是否存在中奖票？如何找到这样的中奖票？本文提出KS-Lottery方法，用于识别大语言模型参数中在多语言微调中高度有效的子集。我们的核心思想是利用Kolmogorov-Smirnov检验分析参数在微调前后的分布变化。我们进一步从理论上证明，KS-Lottery能够在嵌入层中找到经认证的中奖票，且基于所找到参数进行微调的性能保证与全参数微调相当。在翻译任务上，将KS-Lottery与其他参数高效微调算法进行比较，实验结果表明，KS-Lottery能够找到远更小的参数集进行微调，同时达到与全参数微调大语言模型相当的性能。令人惊讶的是，我们发现仅微调LLaMA的18个词元的嵌入就足以达到微调翻译性能。相关代码和模型将向公众开源。