Shivashankar Subramanian, Ioana Baldini, et al.
IAAI 2020
Zero-shot prompt-based learning has made much progress in sentiment analysis, and considerable effort has been dedicated to designing high-performing prompt templates. However, two problems exist; First, large language models are often biased to their pre-training data, leading to poor performance in prompt templates that models have rarely seen. Second, in order to adapt to different domains, re-designing prompt templates is usually required, which is time-consuming and inefficient. To remedy both shortcomings, we propose a simple yet strong data construction method to de-bias a given prompt template, yielding a large performance improvement in sentiment analysis tasks across different domains, pre-trained language models, and prompt templates. Also, we demonstrate the advantage of using domain-agnostic generic responses over the in-domain ground-truth data.
Shivashankar Subramanian, Ioana Baldini, et al.
IAAI 2020
Hammad Ayyubi, Rahul Lokesh, et al.
ACL 2023
Kevin Gu, Eva Tuecke, et al.
ICML 2024
Gabriele Picco, Lam Thanh Hoang, et al.
EMNLP 2021