Recursively Summarizing Books with Human Feedback · HackerPapers discussions

Recursively Summarizing Books with Human Feedback — mentioned by jefftk

Tue, 14 Mar 2023 12:51:01 GMT

Reinforcement learning in general didn't come out of AI alignment work, but RHLF in particular did. The initial idea and paper [1] were from AI alignment folks, as was most of the later development [2][3][4][5]. Overview: https://www.alignmentforum.org/posts/vwu4kegAEZTBtpT6p/thoug... [1] Deep Reinforcement Learning from Human Preferences https://arxiv.org/abs/1706.03741 [2] Fine-Tuning Language Models from Human Preferences https://arxiv.org/abs/1909.08593 [3] Learning to summarize from human feedback https://arxiv.org/abs/2009.01325 [4] Recursively Summarizing Books with Human Feedback…

Paper and discussion history. A mention is not an endorsement.

Recursively Summarizing Books with Human Feedback — mentioned by ggnore7452

Wed, 18 Jan 2023 09:43:38 GMT

there is actually a paper by OpenAI themselves on summarizing long document. essentially, break a longer text into smaller chunks, and run a multi-stage sequential summarization. each chunk uses a trailing window of previous chunk as context, and run this recursively. https://arxiv.org/abs/2109.10862 did a rough implementation myself, works well for articles even 20k tokens. but kind slow because all the additional overlapping runs required. (and more costly)

Paper and discussion history. A mention is not an endorsement.

Recursively Summarizing Books with Human Feedback — mentioned by djoldman

Fri, 24 Sep 2021 16:19:25 GMT

Paper: https://arxiv.org/pdf/2109.10862.pdf

Paper and discussion history. A mention is not an endorsement.