按年被提到
20212023 · 2 次2026
大模型与语言模型›大模型文本、写作与版权·arXiv:2109.10862 · cs.CL

Recursively Summarizing Books with Human Feedback

Jeff Wu, Long Ouyang, Daniel M. Ziegler, Nisan Stiennon, Ryan Lowe, Jan Leike, Paul Christiano · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-01-18 · 最近 2023-03-14
2不同的人
2活跃月份
2讨论串
150被引(OpenAlex)
arXiv 摘要(候选层不写导读)

A major challenge for scaling machine learning is training models to perform tasks that are very difficult or time-consuming for humans to evaluate. We present progress on this problem on the task of abstractive summarization of entire fiction novels. Our method combines learning from human feedback with recursive task decomposition: we use models trained on smaller parts of the task to assist humans in giving feedback on the broader task. We collect a large volume of demonstrations and comparisons from human labelers, and fine-tune GPT-3 using behavioral cloning and reward modeling to do summarization recursively. At inference time, the model first summarizes small sections of the book and then recursively summarizes these summaries to produce a summary of the entire book. Our human labelers are able to supervise and evaluate the models quickly, despite not having read the entire books themselves. Our resulting model generates sensible summaries of entire books, even matching the quality of human-written summaries in a few cases ($\sim5\%$ of books). We achieve state-of-the-art results on the recent BookSum dataset for book-length summarization. A zero-shot question-answering model using these summaries achieves state-of-the-art results on the challenging NarrativeQA benchmark for answering questions about books and movie scripts. We release datasets of samples from our model.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论ggnore7452 · 2023-01

“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 ar…”

Show HN: Summate.it – Quickly summarize web articles with OpenAI原评论 ↗
评论jefftk · 2023-03

“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/thoughts-on-the-impact-of-rlhf-research [1] Deep Reinforcement Learning from Hu…”

Microsoft lays off an ethical AI team as it doubles down on OpenAI原评论 ↗