数据集平衡的局限性:与虚假相关性的失败之战
On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations
摘要:
最近的研究表明,NLP中的深度学习模型对简单特征和特定输出标签之间的低级相关性高度敏感,导致过度拟合和缺乏泛化。为了缓解这个问题,通常的做法是通过添加新实例或通过过滤掉“简单”实例来平衡数据集(Sakaguchi等人,2020年),最终在最近的建议,以消除单字相关性完全(加德纳等人,2021年)。在这篇观点论文中,我们发现,尽管有这些努力,越来越强大的模型不断利用越来越小的虚假相关性,因此,即使平衡所有单字特征也不足以减轻所有这些相关性。同时,一个真正平衡的数据集可能会“把婴儿和洗澡水一起扔掉”,错过重要的信号编码常识和世界知识。我们强调了数据集平衡的几种替代方案,重点是用更丰富的上下文增强数据集,允许模型弃权并与用户交互,并从大规模微调转向零或Few-Shot设置。
英文摘要:
Recent work has shown that deep learning models in NLP are highly sensitive to low-level correlations between simple features and specific output labels, leading to overfitting and lack of generalization. To mitigate this problem, a common practice is to balance datasets by adding new instances or by filtering out "easy" instances (Sakaguchi et al., 2020), culminating in a recent proposal to eliminate single-word correlations altogether (Gardner et al., 2021). In this opinion paper, we identify that despite these efforts, increasingly-powerful models keep exploiting ever-smaller spurious correlations, and as a result even balancing all single-word features is insufficient for mitigating all of these correlations. In parallel, a truly balanced dataset may be bound to "throw the baby out with the bathwater" and miss important signal encoding common sense and world knowledge. We highlight several alternatives to dataset balancing, focusing on enhancing datasets with richer contexts, allowing models to abstain and interact with users, and turning from large-scale fine-tuning to zero- or few-shot setups.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。