Soft-prompt Tuning for Large Language Models to Evaluate Bias

arXiv:2306.04735v2 Announce Type: replace-cross
Abstract: Prompting large language models has gained immense popularity in recent years due to the advantage of producing good results even without the need for labelled data. However, this requires prompt tuning to get optimal prompts that lead to better model performances. In this paper, we explore the use of soft-prompt tuning on sentiment classification task to quantify the biases of large language models (LLMs) such as Open Pre-trained Transformers (OPT) and Galactica language model. Since …

abstract arxiv bias cs.ai cs.cl cs.lg data explore good language language models large language large language models paper performances prompt prompting prompts prompt tuning results type