神经机器翻译中无监督幻觉检测的最优传输方法
Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation
AI总结：
本文针对神经机器翻译中的幻觉检测问题，基于幻觉与源内容脱离导致注意力模式异常的直觉，提出了一种基于最优传输的无监督即插即用检测器，其性能优于现有模型检测器并可媲美大规模监督模型。
摘要：
神经机器翻译（NMT）已成为实际机器翻译应用的事实标准。然而，NMT模型会不可预测地产生严重病态的翻译，即幻觉，这严重破坏了用户信任。因此，实施有效的预防策略以保证其正常运行变得至关重要。在本文中，我们通过一个简单的直觉来解决NMT中的幻觉检测问题：由于幻觉脱离了源内容，它们表现出与高质量翻译在统计上不同的编码器-解码器注意力模式。我们用最优传输公式来构建这个问题，并提出一个完全无监督的、即插即用的检测器，可与任何基于注意力的NMT模型一起使用。实验结果表明，我们的检测器不仅优于以前所有基于模型的检测器，而且与使用在数百万样本上训练的大型模型的检测器具有竞争力。
英文摘要：
Neural machine translation (NMT) has become the de-facto standard in real-world machine translation applications. However, NMT models can unpredictably produce severely pathological translations, known as hallucinations, that seriously undermine user trust. It becomes thus crucial to implement effective preventive strategies to guarantee their proper functioning. In this paper, we address the problem of hallucination detection in NMT by following a simple intuition: as hallucinations are detached from the source content, they exhibit encoder-decoder attention patterns that are statistically different from those of good quality translations. We frame this problem with an optimal transport formulation and propose a fully unsupervised, plug-in detector that can be used with any attention-based NMT model. Experimental results show that our detector not only outperforms all previous model-based detectors, but is also competitive with detectors that employ large models trained on millions of samples.
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。
