Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases

Warning: this paper contains content that may be offensive or upsetting. Detecting social bias in text is challenging due to nuance, subjectivity, and difficulty in obtaining good quality labeled datasets at scale, especially given the evolving nature of social biases and society. To address these challenges, we propose a few-shot instructionbased method for prompting pre-trained language models (LMs). We select a few labelbalanced exemplars from a small support repository that are closest to the query to be labeled in the embedding space. We then provide the LM with instruction that consists of this subset of labeled exemplars, the query text to be classified, a definition of bias, and prompt it to make a decision. We demonstrate that large LMs used in a few-shot context can detect different types of fine-grained biases with similar and sometimes superior accuracy to fine-tuned models. We observe that the largest 530B parameter model is significantly more effective in detecting social bias compared to smaller models (achieving at least 20% improvement in AUC metric compared to other models). It also maintains a high AUC (dropping less than 5%) in a few-shot setting with a labeled repository reduced to as few as 100 samples. Large pretrained language models thus make it easier and quicker to build new bias detectors.