“Reducing Non-Normative Text Generation from Language Models”, 2020-01-23 (; backlinks; similar):
Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. Consequently, they are prone to generating non-normative text (ie. in violation of social norms).
We introduce a technique for fine-tuning GPT-2, using a policy gradient reinforcement learning technique and a normative text classifier to produce reward and punishment values. We evaluate our technique on 5 datasets using automated and human participant experiments.
The normative text classifier is 81–90% accurate when compared to gold-standard human judgments of normative and non-normative generated text.
Our normative fine-tuning technique is able to reduce non-normative text by 27–61%, depending on the dataset.