What Makes Pre-trained Language Models Better Zero-shot Learners?

Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori. This is not ideal because in a real-world zero-shot scenario of practical relevance, no labelled data is available. Thus, we propose a simple yet effective method for screening reasonable prompt templates in zero-shot text classification: Perplexity Selection (Perplection). We hypothesize that language discrepancy can be used to measure the efficacy of prompt templates, and thereby develop a substantiated perplexity-based scheme allowing for forecasting the performance of prompt templates in advance. Experiments show that our method leads to improved prediction performance in a realistic zero-shot setting, eliminating the need for any labelled examples. Dataset 1. [very/not] pleased. 2. [very/not] good. 3. [extremely/less] pleased. 4. [yellow/green] black. PPL Acc.(%) PPL Acc.(%) PPL Acc.(%) PPL Acc.(%)