Statements (21)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
large language model
|
| gptkbp:architecture |
gptkb:transformation
|
| gptkbp:author |
gptkb:Long_Ouyang
gptkb:Jeff_Wu OpenAI Alignment Team |
| gptkbp:developedBy |
gptkb:OpenAI
|
| gptkbp:domain |
natural language processing
|
| https://www.w3.org/2000/01/rdf-schema#label |
IFT-2
|
| gptkbp:language |
English
|
| gptkbp:notablePublication |
https://arxiv.org/abs/2307.15043
Iterative Feedback-Tuning: Aligning Language Models with Human Feedback at Scale |
| gptkbp:predecessor |
gptkb:IFT-1
|
| gptkbp:relatedTo |
gptkb:GPT-4
gptkb:RLHF |
| gptkbp:releaseYear |
2023
|
| gptkbp:trainer |
iterative feedback tuning
|
| gptkbp:usedFor |
AI safety research
alignment research reinforcement learning from human feedback |
| gptkbp:bfsParent |
gptkb:Starship_Integrated_Flight_Test_2
|
| gptkbp:bfsLayer |
6
|