RESEARCH PAPERYear 2020

Learning to summarize with human feedback

Nisan Stiennon; Long Ouyang; Jeffrey Wu; Daniel Ziegler; Ryan Lowe; Chelsea Voss; Alec Radford; Dario Amodei; Paul F. Christiano

Classification

View four quadrants
Major category
Foundational work
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Explicit in survey

Category review. This 2020 work establishes human-preference reward learning and PPO-based language-model post-training. Its output is a summarization policy and learned reward, making it historical post-training background rather than a WAM model component. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX