Transformer一致性训练机制，通过堆叠层间约束提升模型表现与稳定性。
arXiv:2606.05817v1 Announce Type: cross Abstract: Consistency training encourages models to behave similarly across different contexts, and has shown …
ICML 2026 最新研究：一致性训练可能让AI对齐越练越偏，安全性风险不可忽视。
arXiv:2606.03810v1 Announce Type: cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling…
新型对齐范式on-policy一致性训练，在提升LLM安全性同时极小化能力退化，是安全对齐的重要突破。
arXiv:2605.21834v1 Announce Type: new Abstract: Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, o…
用一致性训练算法对抗社交网络政治操纵，为AI安全提供新思路
arXiv:2605.22771v1 Announce Type: new Abstract: Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts.…