Training Language Models to Follow Instructions with Human Feedback
At a glance
InstructGPT uses human feedback to train language models to follow instructions.
In one paragraph
Introduced InstructGPT, using human demonstrations and rankings of responses to train language models that follow instructions more helpfully, with improvements in truthfulness and reduced toxicity.
Authors 20
- Long Ouyang
- Jeffrey Wu
- Xu Jiang
- Diogo Almeida
- Carroll 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
