暂无评分数据
ICLR 2025
Learning through Conditioning on Natural Language Feedback
TL;DR
We explore whether we can finetune language models by letting them generate answers conditioned on prior feedback.
摘要
关键词
Social LearningNatural Language FeedbackInstructive Learning
评审与讨论
作者撤稿通知
In retrospect rushed and not ready for review, don't want to waste reviewers time