Learning to Summarize from Human Feedback

Learning to Summarize from Human Feedback

Yannic Kilcher via YouTube Direct link

- Understanding the Reward Model

10 of 11

10 of 11

- Understanding the Reward Model

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Learning to Summarize from Human Feedback

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - Intro & Overview
  2. 2 - Summarization as a Task
  3. 3 - Problems with the ROUGE Metric
  4. 4 - Training Supervised Models
  5. 5 - Main Results
  6. 6 - Including Human Feedback with Reward Models & RL
  7. 7 - The Unknown Effect of Better Data
  8. 8 - KL Constraint & Connection to Adversarial Examples
  9. 9 - More Results
  10. 10 - Understanding the Reward Model
  11. 11 - Limitations & Broader Impact

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.