Prompting Fairness: Learning Prompts for Debiasing Large Language Models

Abstract

Large language models are prone to internalize social biases due to the characteristics of the data used for their self-supervised training scheme. Considering their recent emergence and wide availability to the general public, it is mandatory to identify and alleviate these biases to avoid perpetuating stereotypes towards underrepresented groups. We present a novel prompt-tuning method for reducing biases in encoder models such as BERT or RoBERTa. Unlike other methods, we only train a small set of additional reusable token embeddings that can be concatenated to any input sequence to reduce bias in the outputs. We particularize this method to gender bias by providing a set of templates used for training the prompts. Evaluations on two benchmarks show that our method is on par with the state of the art while having a limited impact on language modeling ability.