Hypernetworks for Perspectivist Adaptation
This work addresses efficiency issues in perspectivist classification for applications like hate speech detection, though it is incremental as it applies an existing method to a new domain.
The paper tackles the parametric efficiency bottleneck in perspective-aware classification by applying an existing hypernetwork+adapters architecture to perspectivist classification, achieving competitive performance with specialized models on hate speech and toxicity detection while using significantly fewer parameters.
The task of perspective-aware classification introduces a bottleneck in terms of parametric efficiency that did not get enough recognition in existing studies. In this article, we aim to address this issue by applying an existing architecture, the hypernetwork+adapters combination, to perspectivist classification. Ultimately, we arrive at a solution that can compete with specialized models in adopting user perspectives on hate speech and toxicity detection, while also making use of considerably fewer parameters. Our solution is architecture-agnostic and can be applied to a wide range of base models out of the box.