Automatic metrics play a crucial role in machine translation. Despite the widespread use of n-gram-based metrics, there has been a recent surge in the development of pre-trained model-based metrics that focus on measuring sentence semantics. However, these neural metrics, while achieving higher correlations with human evaluations, are often considered to be black boxes with potential biases that are difficult to detect. In this study, we systematically analyze and compare various mainstream and cutting-edge automatic metrics from the perspective of their guidance for training machine translation systems. Through Minimum Risk Training (MRT), we find that certain metrics exhibit robustness defects, such as the presence of universal adversarial translations in BLEURT and BARTScore. In-depth analysis suggests two main causes of these robustness deficits: distribution biases in the training datasets, and the tendency of the metric paradigm. By incorporating token-level constraints, we enhance the robustness of evaluation metrics, which in turn leads to an improvement in the performance of machine translation systems. Codes are available at \url{https://github.com/powerpuffpomelo/fairseq_mrt}.

翻译：自动评价指标在机器翻译中起着关键作用。尽管基于n-gram的指标被广泛使用，但近年来涌现出大量基于预训练模型、专注于衡量句子语义的评价指标。然而，这些神经指标虽与人工评估的相关性更高，却常被视为具有潜在偏差的黑箱，难以检测其缺陷。本研究从指导机器翻译系统训练的角度，系统性地分析和比较了多种主流及前沿自动评价指标。通过最小风险训练（MRT），我们发现部分指标存在鲁棒性缺陷，例如BLEURT和BARTScore中存在通用对抗翻译样本。深入分析表明，这些鲁棒性缺陷主要由两个原因导致：训练数据集的分布偏差，以及评价范式的倾向性。通过引入词元级约束，我们增强了评价指标的鲁棒性，进而提升了机器翻译系统的性能。代码开源地址：\url{https://github.com/powerpuffpomelo/fairseq_mrt}