AI Chronicle · Corrections

InstructGPT 用 RLHF 让模型更好遵循指令

2022-03-04 · instructgpt-2022

Sources this entry has · 1

Training language models to follow instructions with human feedback · arxiv.org

If any of these no longer opens, or does not match what the original says, please say so directly.

Report this entry by email

The mail is prefilled with the entry, the date and the link; you only add what is wrong and the evidence.

No email client

Copy the block below into whichever channel reaches us:

Entry: InstructGPT 用 RLHF 让模型更好遵循指令
Date: 2022-03-04
Page: https://aihist.net/en/e/instructgpt-2022.html
What is wrong: (date / fact / source / the judgement)
Evidence: (a link that opens)

See this entry on the timeline · Back to the site