We show that language model finetuning can be improved, sometimes
dramatically, with a simple augmentation. NEFTune adds noise to the embedding
vectors during training. Standard finetuning of LLaMA-2-7B using Alpaca
achieves 29.79% on AlpacaEval, which rises to 64.69% using noisy embeddings.
NEFTune also improves over strong baselines on modern instruction datasets.
Models trained with Evol-Instruct see a 10% improvement, with ShareGPT an 8%
improvement, and with OpenPlatypus an 8% improvement. Even powerful models
further refined with RLHF such as LLaMA-2-Chat benefit from additional training
with NEFTune.

使用简单的增强方法 NEFTune，对语言模型进行细调可以显著提高性能，在 AlpacaEval 测试中，LLaMA-2-7B 的标准细调结果为 29.79%，而使用带有噪声的嵌入向量增强后提高至 64.69%。NEFTune 还在现代指令数据集上改进了强基准模型，在 Evol-Instruct 数据集上提高了 10%，在 ShareGPT 上提高了 8%，在 OpenPlatypus 上也提高了 8%。对于使用 RLHF 进一步优化的强大模型（如 LLaMA-2-Chat），通过 NEFTune 进行额外训练也带来了益处。

NEFTune: 噪声嵌入改善指令微调

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Unlike mainstream languages (such as English and French), low-resource
languages often suffer from a lack of expert-annotated corpora and benchmark
resources that make it hard to apply state-of-the-art techniques directly. In
this paper, we alleviate this scarcity problem for the low-resourced Filipino
language in two ways. First, we introduce a new benchmark language modeling
dataset in Filipino which we call WikiText-TL-39. Second, we show that language
model finetuning techniques such as BERT and ULMFiT can be used to consistently
train robust classifiers in low-resource settings, experiencing at most a
0.0782 increase in validation error when the number of training examples is
decreased from 10K to 1K while finetuning using a privately-held sentiment
dataset.

我们介绍了一个新的 Filipino 语言建模数据集，并展示了在低资源环境下，采用 BERT 和 ULMFiT 等语言模型微调技术，能够稳定地训练出健壮的分类器。