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.

通过使用外部知识补充上下文，知识感知对话生成旨在减轻文本退化问题，然而，模型经常无法以人类方式将这些信息内化为响应，而仅简单地将所提供的知识片段插入到通用响应中，导致生成的响应往往乏味、不连贯且缺乏互动性，这意味着退化问题仍未解决。在这项工作中，我们首先发现，这种复制式退化主要是由于弱似然目标，这使得模型可以通过仅基于重叠的表面模式匹配来 “欺骗” 这个目标而复制知识片段。为了克服这一挑战，我们提出一种多级自适应对比学习（MACL）框架，该框架动态采样负例，并随后在令牌级别和序列级别上惩罚退化行为。广泛的实验验证了我们的方法在 WoW 数据集上的有效性以及在各种预训练模型上的适用性。