Large Language Models (LLMs) have demonstrated impressive zero shot
performance on a wide range of NLP tasks, demonstrating the ability to reason
and apply commonsense. A relevant application is to use them for creating high
quality synthetic datasets for downstream tasks. In this work, we probe whether
GPT-4 can be used to augment existing extractive reading comprehension
datasets. Automating data annotation processes has the potential to save large
amounts of time, money and effort that goes into manually labelling datasets.
In this paper, we evaluate the performance of GPT-4 as a replacement for human
annotators for low resource reading comprehension tasks, by comparing
performance after fine tuning, and the cost associated with annotation. This
work serves to be the first analysis of LLMs as synthetic data augmenters for
QA systems, highlighting the unique opportunities and challenges. Additionally,
we release augmented versions of low resource datasets, that will allow the
research community to create further benchmarks for evaluation of generated
datasets.

本文探讨了使用 GPT-4 作为人工标注的替代品来提供低资源阅读理解任务的性能，通过精细调节后的性能和标注成本的对比，这是对 LLMs 作为合成数据增广器用于 QA 系统的第一次分析，强调了这一独特的机遇和挑战，并提供了低资源数据集的增广版本，为生成数据集的评估提供了进一步的基准。

LLM 能增强低资源阅读理解数据集吗？机遇和挑战

Can LLMs Augment Low-Resource Reading Comprehension Datasets?  Opportunities and Challenges

Sentiment analysis is a task that may suffer from a lack of data in certain
cases, as the datasets are often generated and annotated by humans. In cases
where data is inadequate for training discriminative models, generate models
may aid training via data augmentation. Generative Adversarial Networks (GANs)
are one such model that has advanced the state of the art in several tasks,
including as image and text generation. In this paper, I train GAN models on
low resource datasets, then use them for the purpose of data augmentation
towards improving sentiment classifier generalization. Given the constraints of
limited data, I explore various techniques to train the GAN models. I also
present an analysis of the quality of generated GAN data as more training data
for the GAN is made available. In this analysis, the generated data is
evaluated as a test set (against a model trained on real data points) as well
as a training set to train classification models. Finally, I also conduct a
visual analysis by projecting the generated and the real data into a
two-dimensional space using the t-Distributed Stochastic Neighbor Embedding
(t-SNE) method.

本文介绍使用生成式对抗网络 (GANs) 模型进行数据增强以改善情感分类器泛化能力的方法，通过对资源有限数据集训练 GAN 模型，并探索不同技术进行 GAN 模型训练，并分析了生成数据的质量以及使用 t-SNE 方法在二维空间中对生成数据和实际数据的可视化分析。