1
Emergent Alignment
大模型能否自查伦理偏差？新研究引入“良心步骤”用DPO训练实现自我对齐与修正。
arXiv:2606.19527v1 Announce Type: new Abstract: Can Large Language Models (LLMs) discern when their own outputs are misaligned with human ethics? And …
2
CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language Models
提出CyberCorrect框架，将控制论闭环反馈引入LLM自我修正，解决现有方法缺乏系统性分析和收敛保证的问题。
arXiv:2605.17305v1 Announce Type: cross Abstract: Large language model (LLM) self-correction -- the ability to detect and fix errors in generated outp…