Verified65% confidenceFactExact time

In 2022, OpenAI systematically transferred RLHF to the language model domain through InstructGPT.

3

Sources

65%

Confidence

Long-term

Relevance

7/11/2026

First Seen

Sources

GPT-5.6 Becomes Microsoft Copilot 365's Preferred Model: An In-Depth Look at the OpenAI-Microsoft Partnership

rss7/10/2026

Related Claims

UnverifiedRLHF 最初由 OpenAI 用于语言模型的对齐训练，后被广泛应用于图像生成领域79% similar UnverifiedRLHF 由 OpenAI 于 2017 年前后系统化，最初用于让模型输出更符合人类价值观72% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/487754

API

curl https://kongchang.com/api/v1/knowledge/claims/487754

MCP

get_claim(id=487754)