Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation
This addresses the issue of text degeneration in dialogue systems for applications like chatbots, but it is incremental as it builds on existing contrastive learning methods.
The paper tackled the problem of knowledge-grounded dialogue generation, where models often copy external knowledge into responses, leading to tedious and incoherent outputs; the proposed Multi-level Adaptive Contrastive Learning framework improved performance, achieving state-of-the-art results on the WoW dataset with concrete gains in metrics like BLEU and F1 scores.
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.