CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification
This addresses a bottleneck in adapting pre-trained language models to tasks with many classes, such as in natural language classification, but is incremental as it builds on existing prefix-tuning methods.
The paper tackles the verbalizer ambiguity problem in prefix-tuning for many-class classification by proposing CCPrefix, which uses instance-dependent soft prefixes from fact-counterfactual pairs, and reports that it outperforms former baselines in experiments on many-class benchmark datasets.
Recently, prefix-tuning was proposed to efficiently adapt pre-trained language models to a broad spectrum of natural language classification tasks. It leverages soft prefix as task-specific indicators and language verbalizers as categorical-label mentions to narrow the formulation gap from pre-training language models. However, when the label space increases considerably (i.e., many-class classification), such a tuning technique suffers from a verbalizer ambiguity problem since the many-class labels are represented by semantic-similar verbalizers in short language phrases. To overcome this, inspired by the human-decision process that the most ambiguous classes would be mulled over for each instance, we propose a brand-new prefix-tuning method, Counterfactual Contrastive Prefix-tuning (CCPrefix), for many-class classification. Basically, an instance-dependent soft prefix, derived from fact-counterfactual pairs in the label space, is leveraged to complement the language verbalizers in many-class classification. We conduct experiments on many-class benchmark datasets in both the fully supervised setting and the few-shot setting, which indicates that our model outperforms former baselines.