Learning from human feedback (RLHF)
No article yet. Other articles already link here, so it is queued for writing.
$ grep -l "Learning from human feedback (RLHF)" ~/wiki
# service page: noindex, so search engines don't treat the site as thin
facts · 2
- ChatGPT launchesEducation · Work & jobs · Media & information · Chatbots · openai.com ↗
- OpenAI describes InstructGPT: the model is fine-tuned on human ratings (RLHF), and people prefer the answers of its 1.3-billion-parameter version to those of the 175-billion-parameter GPT-3Science · Learning from human feedback (RLHF) · arxiv.org ↗