​​Summarizing Books with Human Feedback

OpenAI fine-tuned GPT3 to summarize books well enough to be human-readable. Main approach: recursively split text into parts and then meta-summarize summaries.

This is really important because once there will be a great summarization SOTA we won't need editors to write posts for you. And researchers ultimatively will have some asisstance interpreting models' results.

Read more
ArXiV

#deeplearning #nlp #gpt #transformer

@pythonicAi

Pythonic AI

​​Summarizing Books with Human Feedback

OpenAI fine-tuned GPT3 to summarize books well enough to be human-readable. Main approach: recursively split text into parts and then meta-summarize summaries.

This is really important because once there will be a great summarization SOTA we won't need editors to write posts for you. And researchers ultimatively will have some asisstance interpreting models' results.

Read more
ArXiV

#deeplearning #nlp #gpt #transformer

@pythonicAi

Openai

Summarizing books with human feedback

Scaling human oversight of AI systems for tasks that are difficult to evaluate.

hottg.com/pythonicAI/1190

517 viewsSoroush Hashemifar, Sep 27, 2021 at 09:44