论文标题
寻找一个英俊的木匠！ deapias gpt-3招聘广告
Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements
论文作者
论文摘要
生成语言模型的增长能力和可用性已实现了各种新的下游任务。学术研究已经确定了语言模型中存在，量化和缓解偏见，但很少针对下游的任务量身定制，在这些任务中，人们可以感受到对个人和社会的更广泛影响。在这项工作中，我们利用一种流行的生成语言模型GPT-3，目的是编写公正和现实的招聘广告。我们首先评估了零击产生的广告的偏见和现实主义，并将其与现实世界的广告进行比较。然后，我们将及时的工程和微调评估为借记方法。我们发现，具有多样性的提示及时工程的及时工程没有显着改善偏见，也没有现实主义。相反，微调，尤其是在公正的真实广告上，可以改善现实主义并减少偏见。
The growing capability and availability of generative language models has enabled a wide range of new downstream tasks. Academic research has identified, quantified and mitigated biases present in language models but is rarely tailored to downstream tasks where wider impact on individuals and society can be felt. In this work, we leverage one popular generative language model, GPT-3, with the goal of writing unbiased and realistic job advertisements. We first assess the bias and realism of zero-shot generated advertisements and compare them to real-world advertisements. We then evaluate prompt-engineering and fine-tuning as debiasing methods. We find that prompt-engineering with diversity-encouraging prompts gives no significant improvement to bias, nor realism. Conversely, fine-tuning, especially on unbiased real advertisements, can improve realism and reduce bias.
