Fine Tuning Fake Reviews
David discusses the results of their analysis, revealing that people find it more difficult to detect the fine tuned GPT-2 model compared to the pretrained GPT-2 model. The fine tuning process proves to be more convincing and review-like, making it a valuable tool for NLU practitioners in creating fake reviews.In this clip
From this podcast
Data Skeptic
Sentiment Preserving Fake Reviews
Related Questions