Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context. However, the model often fails to internalize this information into responses in a human-like manner. Instead, it simply inserts segments of the provided knowledge into generic responses. As a result, the generated responses tend to be tedious, incoherent, and in lack of interactivity which means the degeneration problem is still unsolved. In this work, we first find that such copying-style degeneration is primarily due to the weak likelihood objective, which allows the model to "cheat" the objective by merely duplicating knowledge segments in a superficial pattern matching based on overlap. To overcome this challenge, we then propose a Multi-level Adaptive Contrastive Learning (MACL) framework that dynamically samples negative examples and subsequently penalizes degeneration behaviors at both the token-level and sequence-level. Extensive experiments on the WoW dataset demonstrate the effectiveness of our approach across various pre-trained models.

翻译：知识增强的对话生成旨在通过引入外部知识补充上下文来缓解文本退化问题。然而，模型往往无法以类人方式将这些信息内化到回复中，相反，它只是简单地将所提供知识的片段插入到通用回复中。由此生成的回复往往冗长、不连贯且缺乏互动性，这意味着退化问题仍未解决。本文首先发现这种复制式退化主要源于弱似然目标函数——该目标允许模型通过基于重叠的表层模式匹配简单复制知识片段来"欺骗"优化目标。为攻克这一挑战，我们进而提出多层级自适应对比学习（MACL）框架，该框架动态采样负例，并在词元层级和序列层级同时惩罚退化行为。在WoW数据集上的大量实验表明，我们的方法在多种预训练模型上均具有有效性。