What is recorded here?
Combined supervised demonstrations, human preference rankings, a learned reward model and PPO fine-tuning to make GPT-3-derived models better follow instructions on the studied API prompt distribution.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
The record is the twenty-author 2022 paper. Reported preference, truthfulness and toxicity gains are distribution- and evaluator-dependent, and the work does not establish complete alignment or absence of harmful failures.
Read the original work
- OpenAI: Aligning language models to follow instructions
- Ouyang et al., Training language models to follow instructions with human feedback
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Long Ouyang; Jeff Wu; Xu Jiang; Diogo Almeida; Carroll L. Wainwright; Pamela Mishkin; Chong Zhang; Sandhini Agarwal; Katarina Slama; Alex Ray; John Schulman; Jacob Hilton; Fraser Kelton; Luke Miller; Maddie Simens; Amanda Askell; Peter Welinder; Paul Christiano; Jan Leike; Ryan Lowe
The named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Ouyang and colleagues: InstructGPT
Combined supervised demonstrations, human preference rankings, a learned reward model and PPO fine-tuning to make GPT-3-derived models better follow instructions on the studied API prompt distribution.
Scientific scope
The record is the twenty-author 2022 paper. Reported preference, truthfulness and toxicity gains are distribution- and evaluator-dependent, and the work does not establish complete alignment or absence of harmful failures.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Long Ouyang; Jeff Wu; Xu Jiang; Diogo Almeida; Carroll L. Wainwright; Pamela Mishkin; Chong Zhang; Sandhini Agarwal; Katarina Slama; Alex Ray; John Schulman; Jacob Hilton; Fraser Kelton; Luke Miller; Maddie Simens; Amanda Askell; Peter Welinder; Paul Christiano; Jan Leike; Ryan Lowe
The named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.