Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning

Xiangjue Dong, Ziwei Zhu, Zhuoer Wang, Maria Teleki, James Caverlee

Submission Type: Regular Long Paper

Submission Track: Ethics in NLP

Submission Track 2: Language Modeling and Analysis of Language Models

Keywords: bias, contrastive learning, prompt tuning

TL;DR: We propose Co$^2$PT, an efficient and effective method for mitigating biases via counterfactual contrastive prompt tuning on downstream tasks.

Abstract: Pre-trained Language Models are widely used in many important real-world applications. However, recent studies show that these models can encode social biases from large pre-training corpora and even amplify biases in downstream applications. To address this challenge, we propose Co$^2$PT, an efficient and effective *debias-while-prompt tuning* method for mitigating biases via counterfactual contrastive prompt tuning on downstream tasks. Our experiments conducted on three extrinsic bias benchmarks demonstrate the effectiveness of Co$^2$PT on bias mitigation during the prompt tuning process and its adaptability to existing upstream debiased language models. These findings indicate the strength of Co$^2$PT and provide promising avenues for further enhancement in bias mitigation on downstream tasks.

Submission Number: 4378