Материал на языке оригинала: English.
Fine-tuning GPT-2 from human preferences
We’ve fine-tuned the 774M parameter GPT-2 language model using human feedback for various tasks, successfully matching the preferences of the external human labelers, though those preferences did not always match our own. Specifically, for summarization tasks the labelers preferred sentences copied wholesale from the input (we’d only asked them to ensure accuracy), so our models learned to copy. Summarization required 60k human labels; simpler tasks which continue text in various styles required
19 сентября 2019 г. · Источник: OpenAI news
Полный текст доступен у источника.