用语言代理实现大模型自主微调的创新框架，省去人工干预，让微调过程自动化
arXiv:2603.01712v2 Announce Type: replace-cross Abstract: Fine-tuning large language models for vertical domains remains labor-intensive, requiring pr…
揭秘LLM微调中对齐为何脆弱：从参数动态到输出分布的统一视角
arXiv:2605.18309v1 Announce Type: new Abstract: Although Large Language Models (LLMs) achieve strong alignment through supervised fine-tuning and rein…
提出目标条件监督学习新方法，有效平衡LLM微调的成本与效果，无需外部奖励模型。
arXiv:2605.16345v1 Announce Type: new Abstract: Large language models often require fine-tuning to better align their behavior with user intent at dep…
提出用JEPAs审计LLM微调：预测隐含表示而非输出，以提升任务指标。
arXiv:2605.15394v1 Announce Type: cross Abstract: Joint-embedding predictive architectures (JEPAs) propose that a model should learn more useful abstr…