Entity · technique

Recursive Summarization

techniqueactiverecursive-summarization-0c185b3d·1 events·first seen May 20, 2026

Aliases: Recursive Summarization

Co-occurring entities

Reinforcement Learning from Human Feedback OpenAI scalable oversight

More like this (12)

hierarchical summarization Learning to Summarize with Human Feedback Recursive Self-Improvement Iterated Amplification Recurrent Neural Network clinical text summarization A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs A Human-in-the-Loop Corpus for LLM-Based Simplification of Scientific Summaries Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning SummEval RECAP Adaptive Parallel Reasoning

Recent events (1)

5Openai Blog·May 20, 2026·source ↗

Summarizing Books with Human Feedback

OpenAI published research on using human feedback to train models to summarize entire books, addressing the challenge of scaling human oversight to tasks that are difficult for humans to evaluate directly. The work explores recursive task decomposition, where models summarize smaller chunks and then summarize those summaries, with humans providing feedback at each level. This represents an early concrete application of scalable oversight techniques to long-document understanding.

Long Context Evolution AI Safety Research Recursive Summarization Reinforcement Learning from Human Feedback OpenAI +2 more