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

12/15/2021
by   Shrimai Prabhumoye, et al.
22

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 instruction-based method for prompting pre-trained language models (LMs). We select a few label-balanced 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 AUC metric compared to other models). It also maintains a high AUC (dropping less than 5 as 100 samples. Large pretrained language models thus make it easier and quicker to build new bias detectors.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/01/2023

Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias

Recent studies show that instruction tuning and learning from human feed...
research
07/19/2023

Can Instruction Fine-Tuned Language Models Identify Social Bias through Prompting?

As the breadth and depth of language model applications continue to expa...
research
04/18/2021

Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity

When primed with only a handful of training samples, very large pretrain...
research
09/07/2023

OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMs

Instruction-tuned Large Language Models (LLMs) have recently showcased r...
research
05/25/2023

Uncovering and Categorizing Social Biases in Text-to-SQL

Content Warning: This work contains examples that potentially implicate ...
research
04/13/2023

Evaluation of Social Biases in Recent Large Pre-Trained Models

Large pre-trained language models are widely used in the community. Thes...
research
03/15/2023

Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!

Large Language Models (LLMs) have made remarkable strides in various tas...

Please sign up or login with your details

Forgot password? Click here to reset