2 resources

  • Elizabeth Clark, Tal August, Sofia Serra...
    |
    Dec 14th, 2021
    |
    preprint
    Elizabeth Clark, Tal August, Sofia Serra...
    Dec 14th, 2021

    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 and GPT3) in three domains (stories, news articles, and recipes). We find that, without training, evaluators distinguished between GPT3- and human-authored text at random chance level. We explore...

  • Elizabeth Clark, Tal August, Sofia Serra...
    |
    Dec 14th, 2021
    |
    preprint
    Elizabeth Clark, Tal August, Sofia Serra...
    Dec 14th, 2021

    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 and GPT3) in three domains (stories, news articles, and recipes). We find that, without training, evaluators distinguished between GPT3- and human-authored text at random chance level. We explore...

Last update from database: 14/12/2025, 22:15 (UTC)
Powered by Zotero and Kerko.