• About
  • Research
  • Trusted AI
  • Resources
  • Careers
  • Blog
  • About
  • Research
  • Trusted AI
  • Resources
  • Careers
  • Blog
Blog Home

Near-Negative Distinction: Re-Thinking Text Generation Evaluation

We introduce an automated method for evaluating the quality of AI-generated text by repurposing prior human evaluation data. The method is called Near-Negative Distinction.

23 Nov 2022 • #Near-Negative Distinction
Page 1 of 1
Salesforce.com Careers In the Media Github Privacy Terms of Service Cookie Preferences

© Copyright 2020 Salesforce.com, inc. All rights reserved. Rights of ALBERT EINSTEIN are use with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.