← Search

Nikita Haduong

2 accepted papers

2021

All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text

ACL 2021long

Human evaluations are typically considered the gold standard in natural language generation, but as models’ fluency improves, how well can evaluators detect and judge machine-generated text? We run a study assessing non-experts’ ability to distinguish between human- and machine-authored text (GPT2 a…