{"schemaVersion":1,"target":{"type":"reading","id":"e93717af6f94b9a2b0617f61148d125f00cdb5d0f9cfb70a3bc5fce67efe86fd","revision":"f6ae368f-24c1-480a-80ad-f55b512ceefa","revisionKind":"publication-id","title":"Researchers use models’ confidence to train language models","url":"https://escapemeridian.com/readings/researchers-use-models-confidence-to-train-language-models-e93717af"},"source":{"type":"source","id":"https://arxiv.org/abs/2507.21931","revision":"5b14eb4edf48eec5f84fa66a806b5d8deb3999d93bbd0cde6146332b4134986b","revisionKind":"sha256-source-text","title":"Post-Training Large Language Models via Reinforcement Learning from Self-Feedback","url":"https://arxiv.org/abs/2507.21931"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."}